| 1 460 20 227 8 91 291 2097 2097 62 149 2 895 898 737 897 2 896 896 897 738 737 741 737 7 4 1251 15 2 674 278 171 243 200 103 7 7 6 2 15 57 46 63 139 97 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP module. * * Version: @(#)ip.h 1.0.2 05/07/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Changes: * Mike McLagan : Routing by source */ #ifndef _IP_H #define _IP_H #include <linux/types.h> #include <linux/ip.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/sockptr.h> #include <linux/static_key.h> #include <net/inet_sock.h> #include <net/route.h> #include <net/snmp.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/netns/hash.h> #include <net/lwtunnel.h> #include <net/inet_dscp.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ extern unsigned int sysctl_fib_sync_mem; extern unsigned int sysctl_fib_sync_mem_min; extern unsigned int sysctl_fib_sync_mem_max; struct sock; struct inet_skb_parm { int iif; struct ip_options opt; /* Compiled IP options */ u16 flags; #define IPSKB_FORWARDED BIT(0) #define IPSKB_XFRM_TUNNEL_SIZE BIT(1) #define IPSKB_XFRM_TRANSFORMED BIT(2) #define IPSKB_FRAG_COMPLETE BIT(3) #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) #define IPSKB_MULTIPATH BIT(9) #define IPSKB_MCROUTE BIT(10) u16 frag_max_size; }; static inline bool ipv4_l3mdev_skb(u16 flags) { return !!(flags & IPSKB_L3SLAVE); } static inline unsigned int ip_hdrlen(const struct sk_buff *skb) { return ip_hdr(skb)->ihl * 4; } struct ipcm_cookie { struct sockcm_cookie sockc; __be32 addr; int oif; struct ip_options_rcu *opt; __u8 protocol; __u8 ttl; __s16 tos; __u16 gso_size; }; static inline void ipcm_init(struct ipcm_cookie *ipcm) { *ipcm = (struct ipcm_cookie) { .tos = -1 }; } static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, const struct inet_sock *inet) { *ipcm = (struct ipcm_cookie) { .tos = READ_ONCE(inet->tos), }; sockcm_init(&ipcm->sockc, &inet->sk); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) /* return enslaved device index if relevant */ static inline int inet_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) return IPCB(skb)->iif; #endif return 0; } /* Special input handler for packets caught by router alert option. They are selected only by protocol field, and then processed likely local ones; but only if someone wants them! Otherwise, router not running rsvpd will kill RSVP. It is user level problem, what it will make with them. I have no idea, how it will masquearde or NAT them (it is joke, joke :-)), but receiver should be enough clever f.e. to forward mtrace requests, sent to multicast group to reach destination designated router. */ struct ip_ra_chain { struct ip_ra_chain __rcu *next; struct sock *sk; union { void (*destructor)(struct sock *); struct sock *saved_sk; }; struct rcu_head rcu; }; /* IP flags. */ #define IP_CE 0x8000 /* Flag: "Congestion" */ #define IP_DF 0x4000 /* Flag: "Don't Fragment" */ #define IP_MF 0x2000 /* Flag: "More Fragments" */ #define IP_OFFSET 0x1FFF /* "Fragment Offset" part */ #define IP_FRAG_TIME (30 * HZ) /* fragment lifetime */ struct msghdr; struct net_device; struct packet_type; struct rtable; struct sockaddr; int igmp_mc_init(void); /* * Functions provided by ip.c */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); struct ip_fraglist_iter { struct sk_buff *frag; struct iphdr *iph; int offset; unsigned int hlen; }; void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter); static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip_frag_state { bool DF; unsigned int hlen; unsigned int ll_rs; unsigned int mtu; unsigned int left; int offset; int ptr; __be16 not_last_frag; }; void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state); struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos); void ip_init(void); int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int len, int protolen, struct ipcm_cookie *ipc, struct rtable **rt, unsigned int flags); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork); int ip_send_skb(struct net *net, struct sk_buff *skb); int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4); void ip_flush_pending_frames(struct sock *sk); struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) { return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } /* Get the route scope that should be used when sending a packet. */ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, const struct ipcm_cookie *ipc, const struct msghdr *msg) { if (sock_flag(&inet->sk, SOCK_LOCALROUTE) || msg->msg_flags & MSG_DONTROUTE || (ipc->opt && ipc->opt->opt.is_strictroute)) return RT_SCOPE_LINK; return RT_SCOPE_UNIVERSE; } /* datagram.c */ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); void ip4_datagram_release_cb(struct sock *sk); struct ip_reply_arg { struct kvec iov[1]; int flags; __wsum csum; int csumoffset; /* u16 offset of csum in iov[0].iov_base */ /* -1 if not needed */ int bound_dev_if; u8 tos; kuid_t uid; }; #define IP_REPLY_ARG_NOSRCCHECK 1 static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) { return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time, u32 txhash); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) #define __IP_ADD_STATS(net, field, val) __SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) #define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) #define __IP_UPD_PO_STATS(net, field, val) __SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) #define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field) #define __NET_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.net_statistics, field) #define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) #define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) static inline u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) { return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); } unsigned long snmp_fold_field(void __percpu *mib, int offt); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct, size_t syncp_offset); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off); #else static inline u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct, size_t syncp_offset) { return snmp_get_cpu_field(mib, cpu, offct); } static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off) { return snmp_fold_field(mib, offt); } #endif #define snmp_get_cpu_field64_batch(buff64, stats_list, mib_statistic, offset) \ { \ int i, c; \ for_each_possible_cpu(c) { \ for (i = 0; stats_list[i].name; i++) \ buff64[i] += snmp_get_cpu_field64( \ mib_statistic, \ c, stats_list[i].entry, \ offset); \ } \ } #define snmp_get_cpu_field_batch(buff, stats_list, mib_statistic) \ { \ int i, c; \ for_each_possible_cpu(c) { \ for (i = 0; stats_list[i].name; i++) \ buff[i] += snmp_get_cpu_field( \ mib_statistic, \ c, stats_list[i].entry); \ } \ } static inline void inet_get_local_port_range(const struct net *net, int *low, int *high) { u32 range = READ_ONCE(net->ipv4.ip_local_ports.range); *low = range & 0xffff; *high = range >> 16; } bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port) { if (!net->ipv4.sysctl_local_reserved_ports) return false; return test_bit(port, net->ipv4.sysctl_local_reserved_ports); } static inline bool sysctl_dev_name_is_allowed(const char *name) { return strcmp(name, "default") != 0 && strcmp(name, "all") != 0; } static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock); } #else static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) { return false; } static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { return port < PROT_SOCK; } #endif __be32 inet_current_timestamp(void); /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; void ipfrag_init(void); void ip_static_sysctl_init(void); #define IP4_REPLY_MARK(net, mark) \ (READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0) static inline bool ip_is_fragment(const struct iphdr *iph) { return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0; } #ifdef CONFIG_INET #include <net/dst.h> /* The function in 2.2 was invalid, producing wrong result for * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */ static inline int ip_decrease_ttl(struct iphdr *iph) { u32 check = (__force u32)iph->check; check += (__force u32)htons(0x0100); iph->check = (__force __sum16)(check + (check>=0xFFFF)); return --iph->ttl; } static inline dscp_t ip4h_dscp(const struct iphdr *ip4h) { return inet_dsfield_to_dscp(ip4h->tos); } static inline int ip_mtu_locked(const struct dst_entry *dst) { const struct rtable *rt = dst_rtable(dst); return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc != IP_PMTUDISC_INTERFACE && pmtudisc != IP_PMTUDISC_OMIT; } static inline bool ip_sk_use_pmtu(const struct sock *sk) { return READ_ONCE(inet_sk(sk)->pmtudisc) < IP_PMTUDISC_PROBE; } static inline bool ip_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc < IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_OMIT; } static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { const struct rtable *rt = dst_rtable(dst); unsigned int mtu, res; struct net *net; rcu_read_lock(); net = dev_net_rcu(dst_dev(dst)); if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { mtu = rt->rt_pmtu; if (mtu && time_before(jiffies, READ_ONCE(rt->dst.expires))) goto out; } /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; mtu = READ_ONCE(dst_dev(dst)->mtu); if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); res = mtu - lwtunnel_headroom(dst->lwtstate, mtu); rcu_read_unlock(); return res; } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; return ip_dst_mtu_maybe_forward(dst, forwarding); } mtu = min(READ_ONCE(dst_dev(dst)->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len, struct netlink_ext_ack *extack); static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) { if (fib_metrics != &dst_default_metrics && refcount_dec_and_test(&fib_metrics->refcnt)) kfree(fib_metrics); } /* ipv4 and ipv6 both use refcounted metrics if it is not the default */ static inline void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics) { dst_init_metrics(dst, fib_metrics->metrics, true); if (fib_metrics != &dst_default_metrics) { dst->_metrics |= DST_METRICS_REFCOUNTED; refcount_inc(&fib_metrics->refcnt); } } static inline void ip_dst_metrics_put(struct dst_entry *dst) { struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) kfree(p); } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); /* We had many attacks based on IPID, use the private * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { int val; /* avoid atomic operations for TCP, * as we hold socket lock at this point. */ if (sk_is_tcp(sk)) { sock_owned_by_me(sk); val = atomic_read(&inet_sk(sk)->inet_id); atomic_set(&inet_sk(sk)->inet_id, val + segs); } else { val = atomic_add_return(segs, &inet_sk(sk)->inet_id); } iph->id = htons(val); return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { iph->id = 0; } else { /* Unfortunately we need the big hammer to get a suitable IPID */ __ip_select_ident(net, iph, segs); } } static inline void ip_select_ident(struct net *net, struct sk_buff *skb, struct sock *sk) { ip_select_ident_segs(net, skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) { return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len, proto, 0); } /* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v4addrs.src = iph->saddr; * flow->v4addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, const struct iphdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != offsetof(typeof(flow->addrs), v4addrs.src) + sizeof(flow->addrs.v4addrs.src)); memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } /* * Map a multicast IP onto multicast MAC for type ethernet. */ static inline void ip_eth_mc_map(__be32 naddr, char *buf) { __u32 addr=ntohl(naddr); buf[0]=0x01; buf[1]=0x00; buf[2]=0x5e; buf[5]=addr&0xFF; addr>>=8; buf[4]=addr&0xFF; addr>>=8; buf[3]=addr&0x7F; } /* * Map a multicast IP onto multicast MAC for type IP-over-InfiniBand. * Leave P_Key as 0 to be filled in by driver. */ static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf) { __u32 addr; unsigned char scope = broadcast[5] & 0xF; buf[0] = 0; /* Reserved */ buf[1] = 0xff; /* Multicast QPN */ buf[2] = 0xff; buf[3] = 0xff; addr = ntohl(naddr); buf[4] = 0xff; buf[5] = 0x10 | scope; /* scope from broadcast address */ buf[6] = 0x40; /* IPv4 signature */ buf[7] = 0x1b; buf[8] = broadcast[8]; /* P_Key */ buf[9] = broadcast[9]; buf[10] = 0; buf[11] = 0; buf[12] = 0; buf[13] = 0; buf[14] = 0; buf[15] = 0; buf[19] = addr & 0xff; addr >>= 8; buf[18] = addr & 0xff; addr >>= 8; buf[17] = addr & 0xff; addr >>= 8; buf[16] = addr & 0x0f; } static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf) { if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) memcpy(buf, broadcast, 4); else memcpy(buf, &naddr, sizeof(naddr)); } #if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif static __inline__ void inet_reset_saddr(struct sock *sk) { inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); memset(&np->saddr, 0, sizeof(np->saddr)); memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); } #endif } #endif #if IS_MODULE(CONFIG_IPV6) #define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X) #define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X) #else #define EXPORT_IPV6_MOD(X) #define EXPORT_IPV6_MOD_GPL(X) #endif static inline unsigned int ipv4_addr_hash(__be32 ip) { return (__force unsigned int) ip; } static inline u32 __ipv4_addr_hash(const __be32 ip, const u32 initval) { return jhash_1word((__force u32)ip, initval); } static inline u32 ipv4_portaddr_hash(const struct net *net, __be32 saddr, unsigned int port) { return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } bool ip_call_ra_chain(struct sk_buff *skb); /* * Functions provided by ip_fragment.c */ enum ip_defrag_users { IP_DEFRAG_LOCAL_DELIVER, IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP_DEFRAG_CONNTRACK_OUT, __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, IP_DEFRAG_VS_FWD, IP_DEFRAG_AF_PACKET, IP_DEFRAG_MACVLAN, }; /* Return true if the value of 'user' is between 'lower_bond' * and 'upper_bond' inclusively. */ static inline bool ip_defrag_user_in_between(u32 user, enum ip_defrag_users lower_bond, enum ip_defrag_users upper_bond) { return user >= lower_bond && user <= upper_bond; } int ip_defrag(struct net *net, struct sk_buff *skb, u32 user); #ifdef CONFIG_INET struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user); #else static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { return skb; } #endif /* * Functions provided by ip_forward.c */ int ip_forward(struct sk_buff *skb); /* * Functions provided by ip_options.c */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); static inline int ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb) { return __ip_options_echo(net, dopt, skb, &IPCB(skb)->opt); } void ip_options_fragment(struct sk_buff *skb); int __ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb, __be32 *info); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb); int ip_options_get(struct net *net, struct ip_options_rcu **optp, sockptr_t data, int optlen); void ip_options_undo(struct ip_options *opt); void ip_forward_options(struct sk_buff *skb); int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); /* * Functions provided by ip_sockglue.c */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst); void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); DECLARE_STATIC_KEY_FALSE(ip4_min_ttl); int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ip_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, u32 info); static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } bool icmp_global_allow(struct net *net); void icmp_global_consume(struct net *net); #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); #endif int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); static inline bool inetdev_valid_mtu(unsigned int mtu) { return likely(mtu >= IPV4_MIN_MTU); } void ip_sock_set_freebind(struct sock *sk); int ip_sock_set_mtu_discover(struct sock *sk, int val); void ip_sock_set_pktinfo(struct sock *sk); void ip_sock_set_recverr(struct sock *sk); void ip_sock_set_tos(struct sock *sk, int val); void __ip_sock_set_tos(struct sock *sk, int val); #endif /* _IP_H */ |
| 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NetLabel NETLINK Interface * * This file defines the NETLINK interface for the NetLabel system. The * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 */ #ifndef _NETLABEL_USER_H #define _NETLABEL_USER_H #include <linux/types.h> #include <linux/skbuff.h> #include <linux/capability.h> #include <linux/audit.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> /* NetLabel NETLINK helper functions */ /** * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg * @audit_info: NetLabel audit information */ static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { security_current_getlsmprop_subj(&audit_info->prop); audit_info->loginuid = audit_get_loginuid(current); audit_info->sessionid = audit_get_sessionid(current); } /* NetLabel NETLINK I/O functions */ int netlbl_netlink_init(void); /* NetLabel Audit Functions */ struct audit_buffer *netlbl_audit_start_common(int type, struct netlbl_audit *audit_info); #endif |
| 2 2 9 1 1 2 1 4 2 1 1 2 1 1 4 4 8 8 8 2 2 8 1 1 1 1 14 1 1 4 3 1 4 2 1 1 1 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pn_netlink.c * * Phonet netlink interface * * Copyright (C) 2008 Nokia Corporation. * * Authors: Sakari Ailus <sakari.ailus@nokia.com> * Remi Denis-Courmont */ #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/phonet.h> #include <linux/slab.h> #include <net/sock.h> #include <net/phonet/pn_dev.h> /* Device address handling */ static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr, u32 portid, u32 seq, int event); void phonet_address_notify(struct net *net, int event, u32 ifindex, u8 addr) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(1), GFP_KERNEL); if (skb == NULL) goto errout; err = fill_addr(skb, ifindex, addr, 0, 0, event); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_PHONET_IFADDR, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_PHONET_IFADDR, err); } static const struct nla_policy ifa_phonet_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U8 }, }; static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct net_device *dev; struct ifaddrmsg *ifm; int err; u8 pnaddr; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_phonet_policy, extack); if (err < 0) return err; ifm = nlmsg_data(nlh); if (tb[IFA_LOCAL] == NULL) return -EINVAL; pnaddr = nla_get_u8(tb[IFA_LOCAL]); if (pnaddr & 3) /* Phonet addresses only have 6 high-order bits */ return -EINVAL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifm->ifa_index); if (!dev) { rcu_read_unlock(); return -ENODEV; } if (nlh->nlmsg_type == RTM_NEWADDR) err = phonet_address_add(dev, pnaddr); else err = phonet_address_del(dev, pnaddr); rcu_read_unlock(); if (!err) phonet_address_notify(net, nlh->nlmsg_type, ifm->ifa_index, pnaddr); return err; } static int fill_addr(struct sk_buff *skb, u32 ifindex, u8 addr, u32 portid, u32 seq, int event) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), 0); if (nlh == NULL) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_PHONET; ifm->ifa_prefixlen = 0; ifm->ifa_flags = IFA_F_PERMANENT; ifm->ifa_scope = RT_SCOPE_LINK; ifm->ifa_index = ifindex; if (nla_put_u8(skb, IFA_LOCAL, addr)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { int addr_idx = 0, addr_start_idx = cb->args[1]; int dev_idx = 0, dev_start_idx = cb->args[0]; struct phonet_device_list *pndevs; struct phonet_device *pnd; int err = 0; pndevs = phonet_device_list(sock_net(skb->sk)); rcu_read_lock(); list_for_each_entry_rcu(pnd, &pndevs->list, list) { DECLARE_BITMAP(addrs, 64); u8 addr; if (dev_idx > dev_start_idx) addr_start_idx = 0; if (dev_idx++ < dev_start_idx) continue; addr_idx = 0; memcpy(addrs, pnd->addrs, sizeof(pnd->addrs)); for_each_set_bit(addr, addrs, 64) { if (addr_idx++ < addr_start_idx) continue; err = fill_addr(skb, READ_ONCE(pnd->netdev->ifindex), addr << 2, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR); if (err < 0) goto out; } } out: rcu_read_unlock(); cb->args[0] = dev_idx; cb->args[1] = addr_idx; return err; } /* Routes handling */ static int fill_route(struct sk_buff *skb, u32 ifindex, u8 dst, u32 portid, u32 seq, int event) { struct rtmsg *rtm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), 0); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_PHONET; rtm->rtm_dst_len = 6; rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = RT_TABLE_MAIN; rtm->rtm_protocol = RTPROT_STATIC; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; if (nla_put_u8(skb, RTA_DST, dst) || nla_put_u32(skb, RTA_OIF, ifindex)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void rtm_phonet_notify(struct net *net, int event, u32 ifindex, u8 dst) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); if (skb == NULL) goto errout; err = fill_route(skb, ifindex, dst, 0, 0, event); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_PHONET_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_PHONET_ROUTE, err); } static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U8 }, [RTA_OIF] = { .type = NLA_U32 }, }; static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[RTA_MAX+1]; bool sync_needed = false; struct net_device *dev; struct rtmsg *rtm; u32 ifindex; int err; u8 dst; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_phonet_policy, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); if (rtm->rtm_table != RT_TABLE_MAIN || rtm->rtm_type != RTN_UNICAST) return -EINVAL; if (tb[RTA_DST] == NULL || tb[RTA_OIF] == NULL) return -EINVAL; dst = nla_get_u8(tb[RTA_DST]); if (dst & 3) /* Phonet addresses only have 6 high-order bits */ return -EINVAL; ifindex = nla_get_u32(tb[RTA_OIF]); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { rcu_read_unlock(); return -ENODEV; } if (nlh->nlmsg_type == RTM_NEWROUTE) { err = phonet_route_add(dev, dst); } else { err = phonet_route_del(dev, dst); if (!err) sync_needed = true; } rcu_read_unlock(); if (sync_needed) { synchronize_rcu(); dev_put(dev); } if (!err) rtm_phonet_notify(net, nlh->nlmsg_type, ifindex, dst); return err; } static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int err = 0; u8 addr; rcu_read_lock(); for (addr = cb->args[0]; addr < 64; addr++) { struct net_device *dev = phonet_route_get_rcu(net, addr << 2); if (!dev) continue; err = fill_route(skb, READ_ONCE(dev->ifindex), addr << 2, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE); if (err < 0) break; } rcu_read_unlock(); cb->args[0] = addr; return err; } static const struct rtnl_msg_handler phonet_rtnl_msg_handlers[] __initdata_or_module = { {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_NEWADDR, .doit = addr_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_DELADDR, .doit = addr_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_GETADDR, .dumpit = getaddr_dumpit, .flags = RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_NEWROUTE, .doit = route_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_DELROUTE, .doit = route_doit, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_PHONET, .msgtype = RTM_GETROUTE, .dumpit = route_dumpit, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; int __init phonet_netlink_register(void) { return rtnl_register_many(phonet_rtnl_msg_handlers); } |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2017 Facebook */ #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/build_bug.h> #include <linux/debugfs.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static int queue_poll_stat_show(void *data, struct seq_file *m) { return 0; } static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos) __acquires(&q->requeue_lock) { struct request_queue *q = m->private; spin_lock_irq(&q->requeue_lock); return seq_list_start(&q->requeue_list, *pos); } static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos) { struct request_queue *q = m->private; return seq_list_next(v, &q->requeue_list, pos); } static void queue_requeue_list_stop(struct seq_file *m, void *v) __releases(&q->requeue_lock) { struct request_queue *q = m->private; spin_unlock_irq(&q->requeue_lock); } static const struct seq_operations queue_requeue_list_seq_ops = { .start = queue_requeue_list_start, .next = queue_requeue_list_next, .stop = queue_requeue_list_stop, .show = blk_mq_debugfs_rq_show, }; static int blk_flags_show(struct seq_file *m, const unsigned long flags, const char *const *flag_name, int flag_name_count) { bool sep = false; int i; for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) { if (!(flags & BIT(i))) continue; if (sep) seq_puts(m, "|"); sep = true; if (i < flag_name_count && flag_name[i]) seq_puts(m, flag_name[i]); else seq_printf(m, "%d", i); } return 0; } static int queue_pm_only_show(void *data, struct seq_file *m) { struct request_queue *q = data; seq_printf(m, "%d\n", atomic_read(&q->pm_only)); return 0; } #define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(DYING), QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), QUEUE_FLAG_NAME(FAIL_IO), QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(INIT_DONE), QUEUE_FLAG_NAME(STATS), QUEUE_FLAG_NAME(REGISTERED), QUEUE_FLAG_NAME(QUIESCED), QUEUE_FLAG_NAME(RQ_ALLOC_TIME), QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(SQ_SCHED), QUEUE_FLAG_NAME(DISABLE_WBT_DEF), QUEUE_FLAG_NAME(NO_ELV_SWITCH), }; #undef QUEUE_FLAG_NAME static int queue_state_show(void *data, struct seq_file *m) { struct request_queue *q = data; BUILD_BUG_ON(ARRAY_SIZE(blk_queue_flag_name) != QUEUE_FLAG_MAX); blk_flags_show(m, q->queue_flags, blk_queue_flag_name, ARRAY_SIZE(blk_queue_flag_name)); seq_puts(m, "\n"); return 0; } static ssize_t queue_state_write(void *data, const char __user *buf, size_t count, loff_t *ppos) { struct request_queue *q = data; char opbuf[16] = { }, *op; /* * The "state" attribute is removed when the queue is removed. Don't * allow setting the state on a dying queue to avoid a use-after-free. */ if (blk_queue_dying(q)) return -ENOENT; if (count >= sizeof(opbuf)) { pr_err("%s: operation too long\n", __func__); goto inval; } if (copy_from_user(opbuf, buf, count)) return -EFAULT; op = strstrip(opbuf); if (strcmp(op, "run") == 0) { blk_mq_run_hw_queues(q, true); } else if (strcmp(op, "start") == 0) { blk_mq_start_stopped_hw_queues(q, true); } else if (strcmp(op, "kick") == 0) { blk_mq_kick_requeue_list(q); } else { pr_err("%s: unsupported operation '%s'\n", __func__, op); inval: pr_err("%s: use 'run', 'start' or 'kick'\n", __func__); return -EINVAL; } return count; } static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = { { "poll_stat", 0400, queue_poll_stat_show }, { "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops }, { "pm_only", 0600, queue_pm_only_show, NULL }, { "state", 0600, queue_state_show, queue_state_write }, { "zone_wplugs", 0400, queue_zone_wplugs_show, NULL }, { }, }; #define HCTX_STATE_NAME(name) [BLK_MQ_S_##name] = #name static const char *const hctx_state_name[] = { HCTX_STATE_NAME(STOPPED), HCTX_STATE_NAME(TAG_ACTIVE), HCTX_STATE_NAME(SCHED_RESTART), HCTX_STATE_NAME(INACTIVE), }; #undef HCTX_STATE_NAME static int hctx_state_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; BUILD_BUG_ON(ARRAY_SIZE(hctx_state_name) != BLK_MQ_S_MAX); blk_flags_show(m, hctx->state, hctx_state_name, ARRAY_SIZE(hctx_state_name)); seq_puts(m, "\n"); return 0; } #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name static const char *const hctx_flag_name[] = { HCTX_FLAG_NAME(TAG_QUEUE_SHARED), HCTX_FLAG_NAME(STACKING), HCTX_FLAG_NAME(TAG_HCTX_SHARED), HCTX_FLAG_NAME(BLOCKING), HCTX_FLAG_NAME(TAG_RR), HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT), }; #undef HCTX_FLAG_NAME static int hctx_flags_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) != ilog2(BLK_MQ_F_MAX)); blk_flags_show(m, hctx->flags, hctx_flag_name, ARRAY_SIZE(hctx_flag_name)); seq_puts(m, "\n"); return 0; } #define CMD_FLAG_NAME(name) [__REQ_##name] = #name static const char *const cmd_flag_name[] = { CMD_FLAG_NAME(FAILFAST_DEV), CMD_FLAG_NAME(FAILFAST_TRANSPORT), CMD_FLAG_NAME(FAILFAST_DRIVER), CMD_FLAG_NAME(SYNC), CMD_FLAG_NAME(META), CMD_FLAG_NAME(PRIO), CMD_FLAG_NAME(NOMERGE), CMD_FLAG_NAME(IDLE), CMD_FLAG_NAME(INTEGRITY), CMD_FLAG_NAME(FUA), CMD_FLAG_NAME(PREFLUSH), CMD_FLAG_NAME(RAHEAD), CMD_FLAG_NAME(BACKGROUND), CMD_FLAG_NAME(NOWAIT), CMD_FLAG_NAME(POLLED), CMD_FLAG_NAME(ALLOC_CACHE), CMD_FLAG_NAME(SWAP), CMD_FLAG_NAME(DRV), CMD_FLAG_NAME(FS_PRIVATE), CMD_FLAG_NAME(ATOMIC), CMD_FLAG_NAME(NOUNMAP), }; #undef CMD_FLAG_NAME #define RQF_NAME(name) [__RQF_##name] = #name static const char *const rqf_name[] = { RQF_NAME(STARTED), RQF_NAME(FLUSH_SEQ), RQF_NAME(MIXED_MERGE), RQF_NAME(DONTPREP), RQF_NAME(SCHED_TAGS), RQF_NAME(USE_SCHED), RQF_NAME(FAILED), RQF_NAME(QUIET), RQF_NAME(IO_STAT), RQF_NAME(PM), RQF_NAME(HASHED), RQF_NAME(STATS), RQF_NAME(SPECIAL_PAYLOAD), RQF_NAME(ZONE_WRITE_PLUGGING), RQF_NAME(TIMED_OUT), RQF_NAME(RESV), }; #undef RQF_NAME static const char *const blk_mq_rq_state_name_array[] = { [MQ_RQ_IDLE] = "idle", [MQ_RQ_IN_FLIGHT] = "in_flight", [MQ_RQ_COMPLETE] = "complete", }; static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state) { if (WARN_ON_ONCE((unsigned int)rq_state >= ARRAY_SIZE(blk_mq_rq_state_name_array))) return "(?)"; return blk_mq_rq_state_name_array[rq_state]; } int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) { const struct blk_mq_ops *const mq_ops = rq->q->mq_ops; const enum req_op op = req_op(rq); const char *op_str = blk_op_str(op); BUILD_BUG_ON(ARRAY_SIZE(cmd_flag_name) != __REQ_NR_BITS); BUILD_BUG_ON(ARRAY_SIZE(rqf_name) != __RQF_BITS); seq_printf(m, "%p {.op=", rq); if (strcmp(op_str, "UNKNOWN") == 0) seq_printf(m, "%u", op); else seq_printf(m, "%s", op_str); seq_puts(m, ", .cmd_flags="); blk_flags_show(m, (__force unsigned int)(rq->cmd_flags & ~REQ_OP_MASK), cmd_flag_name, ARRAY_SIZE(cmd_flag_name)); seq_puts(m, ", .rq_flags="); blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name, ARRAY_SIZE(rqf_name)); seq_printf(m, ", .state=%s", blk_mq_rq_state_name(blk_mq_rq_state(rq))); seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag, rq->internal_tag); if (mq_ops->show_rq) mq_ops->show_rq(m, rq); seq_puts(m, "}\n"); return 0; } EXPORT_SYMBOL_GPL(__blk_mq_debugfs_rq_show); int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) { return __blk_mq_debugfs_rq_show(m, list_entry_rq(v)); } EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show); static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos) __acquires(&hctx->lock) { struct blk_mq_hw_ctx *hctx = m->private; spin_lock(&hctx->lock); return seq_list_start(&hctx->dispatch, *pos); } static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos) { struct blk_mq_hw_ctx *hctx = m->private; return seq_list_next(v, &hctx->dispatch, pos); } static void hctx_dispatch_stop(struct seq_file *m, void *v) __releases(&hctx->lock) { struct blk_mq_hw_ctx *hctx = m->private; spin_unlock(&hctx->lock); } static const struct seq_operations hctx_dispatch_seq_ops = { .start = hctx_dispatch_start, .next = hctx_dispatch_next, .stop = hctx_dispatch_stop, .show = blk_mq_debugfs_rq_show, }; struct show_busy_params { struct seq_file *m; struct blk_mq_hw_ctx *hctx; }; /* * Note: the state of a request may change while this function is in progress, * e.g. due to a concurrent blk_mq_finish_request() call. Returns true to * keep iterating requests. */ static bool hctx_show_busy_rq(struct request *rq, void *data) { const struct show_busy_params *params = data; if (rq->mq_hctx == params->hctx) __blk_mq_debugfs_rq_show(params->m, rq); return true; } static int hctx_busy_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct show_busy_params params = { .m = m, .hctx = hctx }; int res; res = mutex_lock_interruptible(&hctx->queue->elevator_lock); if (res) return res; blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq, ¶ms); mutex_unlock(&hctx->queue->elevator_lock); return 0; } static const char *const hctx_types[] = { [HCTX_TYPE_DEFAULT] = "default", [HCTX_TYPE_READ] = "read", [HCTX_TYPE_POLL] = "poll", }; static int hctx_type_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; BUILD_BUG_ON(ARRAY_SIZE(hctx_types) != HCTX_MAX_TYPES); seq_printf(m, "%s\n", hctx_types[hctx->type]); return 0; } static int hctx_ctx_map_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; sbitmap_bitmap_show(&hctx->ctx_map, m); return 0; } static void blk_mq_debugfs_tags_show(struct seq_file *m, struct blk_mq_tags *tags) { seq_printf(m, "nr_tags=%u\n", tags->nr_tags); seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags); seq_printf(m, "active_queues=%d\n", READ_ONCE(tags->active_queues)); seq_puts(m, "\nbitmap_tags:\n"); sbitmap_queue_show(&tags->bitmap_tags, m); if (tags->nr_reserved_tags) { seq_puts(m, "\nbreserved_tags:\n"); sbitmap_queue_show(&tags->breserved_tags, m); } } static int hctx_tags_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct request_queue *q = hctx->queue; int res; res = mutex_lock_interruptible(&q->elevator_lock); if (res) return res; if (hctx->tags) blk_mq_debugfs_tags_show(m, hctx->tags); mutex_unlock(&q->elevator_lock); return 0; } static int hctx_tags_bitmap_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct request_queue *q = hctx->queue; int res; res = mutex_lock_interruptible(&q->elevator_lock); if (res) return res; if (hctx->tags) sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m); mutex_unlock(&q->elevator_lock); return 0; } static int hctx_sched_tags_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct request_queue *q = hctx->queue; int res; res = mutex_lock_interruptible(&q->elevator_lock); if (res) return res; if (hctx->sched_tags) blk_mq_debugfs_tags_show(m, hctx->sched_tags); mutex_unlock(&q->elevator_lock); return 0; } static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; struct request_queue *q = hctx->queue; int res; res = mutex_lock_interruptible(&q->elevator_lock); if (res) return res; if (hctx->sched_tags) sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m); mutex_unlock(&q->elevator_lock); return 0; } static int hctx_active_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; seq_printf(m, "%d\n", __blk_mq_active_requests(hctx)); return 0; } static int hctx_dispatch_busy_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; seq_printf(m, "%u\n", hctx->dispatch_busy); return 0; } #define CTX_RQ_SEQ_OPS(name, type) \ static void *ctx_##name##_rq_list_start(struct seq_file *m, loff_t *pos) \ __acquires(&ctx->lock) \ { \ struct blk_mq_ctx *ctx = m->private; \ \ spin_lock(&ctx->lock); \ return seq_list_start(&ctx->rq_lists[type], *pos); \ } \ \ static void *ctx_##name##_rq_list_next(struct seq_file *m, void *v, \ loff_t *pos) \ { \ struct blk_mq_ctx *ctx = m->private; \ \ return seq_list_next(v, &ctx->rq_lists[type], pos); \ } \ \ static void ctx_##name##_rq_list_stop(struct seq_file *m, void *v) \ __releases(&ctx->lock) \ { \ struct blk_mq_ctx *ctx = m->private; \ \ spin_unlock(&ctx->lock); \ } \ \ static const struct seq_operations ctx_##name##_rq_list_seq_ops = { \ .start = ctx_##name##_rq_list_start, \ .next = ctx_##name##_rq_list_next, \ .stop = ctx_##name##_rq_list_stop, \ .show = blk_mq_debugfs_rq_show, \ } CTX_RQ_SEQ_OPS(default, HCTX_TYPE_DEFAULT); CTX_RQ_SEQ_OPS(read, HCTX_TYPE_READ); CTX_RQ_SEQ_OPS(poll, HCTX_TYPE_POLL); static int blk_mq_debugfs_show(struct seq_file *m, void *v) { const struct blk_mq_debugfs_attr *attr = m->private; void *data = d_inode(m->file->f_path.dentry->d_parent)->i_private; return attr->show(data, m); } static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *m = file->private_data; const struct blk_mq_debugfs_attr *attr = m->private; void *data = d_inode(file->f_path.dentry->d_parent)->i_private; /* * Attributes that only implement .seq_ops are read-only and 'attr' is * the same with 'data' in this case. */ if (attr == data || !attr->write) return -EPERM; return attr->write(data, buf, count, ppos); } static int blk_mq_debugfs_open(struct inode *inode, struct file *file) { const struct blk_mq_debugfs_attr *attr = inode->i_private; void *data = d_inode(file->f_path.dentry->d_parent)->i_private; struct seq_file *m; int ret; if (attr->seq_ops) { ret = seq_open(file, attr->seq_ops); if (!ret) { m = file->private_data; m->private = data; } return ret; } if (WARN_ON_ONCE(!attr->show)) return -EPERM; return single_open(file, blk_mq_debugfs_show, inode->i_private); } static int blk_mq_debugfs_release(struct inode *inode, struct file *file) { const struct blk_mq_debugfs_attr *attr = inode->i_private; if (attr->show) return single_release(inode, file); return seq_release(inode, file); } static const struct file_operations blk_mq_debugfs_fops = { .open = blk_mq_debugfs_open, .read = seq_read, .write = blk_mq_debugfs_write, .llseek = seq_lseek, .release = blk_mq_debugfs_release, }; static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"state", 0400, hctx_state_show}, {"flags", 0400, hctx_flags_show}, {"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops}, {"busy", 0400, hctx_busy_show}, {"ctx_map", 0400, hctx_ctx_map_show}, {"tags", 0400, hctx_tags_show}, {"tags_bitmap", 0400, hctx_tags_bitmap_show}, {"sched_tags", 0400, hctx_sched_tags_show}, {"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show}, {"active", 0400, hctx_active_show}, {"dispatch_busy", 0400, hctx_dispatch_busy_show}, {"type", 0400, hctx_type_show}, {}, }; static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { {"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops}, {"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops}, {"poll_rq_list", 0400, .seq_ops = &ctx_poll_rq_list_seq_ops}, {}, }; static void debugfs_create_files(struct dentry *parent, void *data, const struct blk_mq_debugfs_attr *attr) { if (IS_ERR_OR_NULL(parent)) return; d_inode(parent)->i_private = data; for (; attr->name; attr++) debugfs_create_file(attr->name, attr->mode, parent, (void *)attr, &blk_mq_debugfs_fops); } void blk_mq_debugfs_register(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs); queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->debugfs_dir) blk_mq_debugfs_register_hctx(q, hctx); } if (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; while (rqos) { blk_mq_debugfs_register_rqos(rqos); rqos = rqos->next; } } } static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { struct dentry *ctx_dir; char name[20]; snprintf(name, sizeof(name), "cpu%u", ctx->cpu); ctx_dir = debugfs_create_dir(name, hctx->debugfs_dir); debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs); } void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { struct blk_mq_ctx *ctx; char name[20]; int i; if (!q->debugfs_dir) return; snprintf(name, sizeof(name), "hctx%u", hctx->queue_num); hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir); debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs); hctx_for_each_ctx(hctx, ctx, i) blk_mq_debugfs_register_ctx(hctx, ctx); } void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx) { if (!hctx->queue->debugfs_dir) return; debugfs_remove_recursive(hctx->debugfs_dir); hctx->sched_debugfs_dir = NULL; hctx->debugfs_dir = NULL; } void blk_mq_debugfs_register_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_debugfs_register_hctx(q, hctx); } void blk_mq_debugfs_unregister_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_debugfs_unregister_hctx(hctx); } void blk_mq_debugfs_register_sched(struct request_queue *q) { struct elevator_type *e = q->elevator->type; lockdep_assert_held(&q->debugfs_mutex); /* * If the parent directory has not been created yet, return, we will be * called again later on and the directory/files will be created then. */ if (!q->debugfs_dir) return; if (!e->queue_debugfs_attrs) return; q->sched_debugfs_dir = debugfs_create_dir("sched", q->debugfs_dir); debugfs_create_files(q->sched_debugfs_dir, q, e->queue_debugfs_attrs); } void blk_mq_debugfs_unregister_sched(struct request_queue *q) { lockdep_assert_held(&q->debugfs_mutex); debugfs_remove_recursive(q->sched_debugfs_dir); q->sched_debugfs_dir = NULL; } static const char *rq_qos_id_to_name(enum rq_qos_id id) { switch (id) { case RQ_QOS_WBT: return "wbt"; case RQ_QOS_LATENCY: return "latency"; case RQ_QOS_COST: return "cost"; } return "unknown"; } void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { lockdep_assert_held(&rqos->disk->queue->debugfs_mutex); if (!rqos->disk->queue->debugfs_dir) return; debugfs_remove_recursive(rqos->debugfs_dir); rqos->debugfs_dir = NULL; } void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) { struct request_queue *q = rqos->disk->queue; const char *dir_name = rq_qos_id_to_name(rqos->id); lockdep_assert_held(&q->debugfs_mutex); if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs) return; if (!q->rqos_debugfs_dir) q->rqos_debugfs_dir = debugfs_create_dir("rqos", q->debugfs_dir); rqos->debugfs_dir = debugfs_create_dir(dir_name, q->rqos_debugfs_dir); debugfs_create_files(rqos->debugfs_dir, rqos, rqos->ops->debugfs_attrs); } void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { struct elevator_type *e = q->elevator->type; lockdep_assert_held(&q->debugfs_mutex); /* * If the parent debugfs directory has not been created yet, return; * We will be called again later on with appropriate parent debugfs * directory from blk_register_queue() */ if (!hctx->debugfs_dir) return; if (!e->hctx_debugfs_attrs) return; hctx->sched_debugfs_dir = debugfs_create_dir("sched", hctx->debugfs_dir); debugfs_create_files(hctx->sched_debugfs_dir, hctx, e->hctx_debugfs_attrs); } void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx) { lockdep_assert_held(&hctx->queue->debugfs_mutex); if (!hctx->queue->debugfs_dir) return; debugfs_remove_recursive(hctx->sched_debugfs_dir); hctx->sched_debugfs_dir = NULL; } |
| 4 2 2 1 1 1 1 5 2 3 5 4 1 5 5 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linear symmetric key cipher operations. * * Generic encrypt/decrypt wrapper for ciphers. * * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <net/netlink.h> #include "skcipher.h" static inline struct crypto_lskcipher *__crypto_lskcipher_cast( struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_lskcipher, base); } static inline struct lskcipher_alg *__crypto_lskcipher_alg( struct crypto_alg *alg) { return container_of(alg, struct lskcipher_alg, co.base); } static int lskcipher_setkey_unaligned(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen) { unsigned long alignmask = crypto_lskcipher_alignmask(tfm); struct lskcipher_alg *cipher = crypto_lskcipher_alg(tfm); u8 *buffer, *alignbuffer; unsigned long absize; int ret; absize = keylen + alignmask; buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = cipher->setkey(tfm, alignbuffer, keylen); kfree_sensitive(buffer); return ret; } int crypto_lskcipher_setkey(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen) { unsigned long alignmask = crypto_lskcipher_alignmask(tfm); struct lskcipher_alg *cipher = crypto_lskcipher_alg(tfm); if (keylen < cipher->co.min_keysize || keylen > cipher->co.max_keysize) return -EINVAL; if ((unsigned long)key & alignmask) return lskcipher_setkey_unaligned(tfm, key, keylen); else return cipher->setkey(tfm, key, keylen); } EXPORT_SYMBOL_GPL(crypto_lskcipher_setkey); static int crypto_lskcipher_crypt_unaligned( struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv, u32 flags)) { unsigned statesize = crypto_lskcipher_statesize(tfm); unsigned ivsize = crypto_lskcipher_ivsize(tfm); unsigned bs = crypto_lskcipher_blocksize(tfm); unsigned cs = crypto_lskcipher_chunksize(tfm); int err; u8 *tiv; u8 *p; BUILD_BUG_ON(MAX_CIPHER_BLOCKSIZE > PAGE_SIZE || MAX_CIPHER_ALIGNMASK >= PAGE_SIZE); tiv = kmalloc(PAGE_SIZE, GFP_ATOMIC); if (!tiv) return -ENOMEM; memcpy(tiv, iv, ivsize + statesize); p = kmalloc(PAGE_SIZE, GFP_ATOMIC); err = -ENOMEM; if (!p) goto out; while (len >= bs) { unsigned chunk = min((unsigned)PAGE_SIZE, len); int err; if (chunk > cs) chunk &= ~(cs - 1); memcpy(p, src, chunk); err = crypt(tfm, p, p, chunk, tiv, CRYPTO_LSKCIPHER_FLAG_FINAL); if (err) goto out; memcpy(dst, p, chunk); src += chunk; dst += chunk; len -= chunk; } err = len ? -EINVAL : 0; out: memcpy(iv, tiv, ivsize + statesize); kfree_sensitive(p); kfree_sensitive(tiv); return err; } static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv, u32 flags)) { unsigned long alignmask = crypto_lskcipher_alignmask(tfm); if (((unsigned long)src | (unsigned long)dst | (unsigned long)iv) & alignmask) return crypto_lskcipher_crypt_unaligned(tfm, src, dst, len, iv, crypt); return crypt(tfm, src, dst, len, iv, CRYPTO_LSKCIPHER_FLAG_FINAL); } int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv) { struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm); return crypto_lskcipher_crypt(tfm, src, dst, len, iv, alg->encrypt); } EXPORT_SYMBOL_GPL(crypto_lskcipher_encrypt); int crypto_lskcipher_decrypt(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *iv) { struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm); return crypto_lskcipher_crypt(tfm, src, dst, len, iv, alg->decrypt); } EXPORT_SYMBOL_GPL(crypto_lskcipher_decrypt); static int crypto_lskcipher_crypt_sg(struct skcipher_request *req, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *ivs, u32 flags)) { struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher); u8 *ivs = skcipher_request_ctx(req); struct crypto_lskcipher *tfm = *ctx; struct skcipher_walk walk; unsigned ivsize; u32 flags; int err; ivsize = crypto_lskcipher_ivsize(tfm); ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(skcipher) + 1); memcpy(ivs, req->iv, ivsize); flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP; if (req->base.flags & CRYPTO_SKCIPHER_REQ_CONT) flags |= CRYPTO_LSKCIPHER_FLAG_CONT; if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL)) flags |= CRYPTO_LSKCIPHER_FLAG_FINAL; err = skcipher_walk_virt(&walk, req, false); while (walk.nbytes) { err = crypt(tfm, walk.src.virt.addr, walk.dst.virt.addr, walk.nbytes, ivs, flags & ~(walk.nbytes == walk.total ? 0 : CRYPTO_LSKCIPHER_FLAG_FINAL)); err = skcipher_walk_done(&walk, err); flags |= CRYPTO_LSKCIPHER_FLAG_CONT; } memcpy(req->iv, ivs, ivsize); return err; } int crypto_lskcipher_encrypt_sg(struct skcipher_request *req) { struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher); struct lskcipher_alg *alg = crypto_lskcipher_alg(*ctx); return crypto_lskcipher_crypt_sg(req, alg->encrypt); } int crypto_lskcipher_decrypt_sg(struct skcipher_request *req) { struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher); struct lskcipher_alg *alg = crypto_lskcipher_alg(*ctx); return crypto_lskcipher_crypt_sg(req, alg->decrypt); } static void crypto_lskcipher_exit_tfm(struct crypto_tfm *tfm) { struct crypto_lskcipher *skcipher = __crypto_lskcipher_cast(tfm); struct lskcipher_alg *alg = crypto_lskcipher_alg(skcipher); alg->exit(skcipher); } static int crypto_lskcipher_init_tfm(struct crypto_tfm *tfm) { struct crypto_lskcipher *skcipher = __crypto_lskcipher_cast(tfm); struct lskcipher_alg *alg = crypto_lskcipher_alg(skcipher); if (alg->exit) skcipher->base.exit = crypto_lskcipher_exit_tfm; if (alg->init) return alg->init(skcipher); return 0; } static void crypto_lskcipher_free_instance(struct crypto_instance *inst) { struct lskcipher_instance *skcipher = container_of(inst, struct lskcipher_instance, s.base); skcipher->free(skcipher); } static void __maybe_unused crypto_lskcipher_show( struct seq_file *m, struct crypto_alg *alg) { struct lskcipher_alg *skcipher = __crypto_lskcipher_alg(alg); seq_printf(m, "type : lskcipher\n"); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "min keysize : %u\n", skcipher->co.min_keysize); seq_printf(m, "max keysize : %u\n", skcipher->co.max_keysize); seq_printf(m, "ivsize : %u\n", skcipher->co.ivsize); seq_printf(m, "chunksize : %u\n", skcipher->co.chunksize); seq_printf(m, "statesize : %u\n", skcipher->co.statesize); } static int __maybe_unused crypto_lskcipher_report( struct sk_buff *skb, struct crypto_alg *alg) { struct lskcipher_alg *skcipher = __crypto_lskcipher_alg(alg); struct crypto_report_blkcipher rblkcipher; memset(&rblkcipher, 0, sizeof(rblkcipher)); strscpy(rblkcipher.type, "lskcipher", sizeof(rblkcipher.type)); strscpy(rblkcipher.geniv, "<none>", sizeof(rblkcipher.geniv)); rblkcipher.blocksize = alg->cra_blocksize; rblkcipher.min_keysize = skcipher->co.min_keysize; rblkcipher.max_keysize = skcipher->co.max_keysize; rblkcipher.ivsize = skcipher->co.ivsize; return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER, sizeof(rblkcipher), &rblkcipher); } static const struct crypto_type crypto_lskcipher_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_lskcipher_init_tfm, .free = crypto_lskcipher_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_lskcipher_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_lskcipher_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_LSKCIPHER, .tfmsize = offsetof(struct crypto_lskcipher, base), .algsize = offsetof(struct lskcipher_alg, co.base), }; static void crypto_lskcipher_exit_tfm_sg(struct crypto_tfm *tfm) { struct crypto_lskcipher **ctx = crypto_tfm_ctx(tfm); crypto_free_lskcipher(*ctx); } int crypto_init_lskcipher_ops_sg(struct crypto_tfm *tfm) { struct crypto_lskcipher **ctx = crypto_tfm_ctx(tfm); struct crypto_alg *calg = tfm->__crt_alg; struct crypto_lskcipher *skcipher; if (!crypto_mod_get(calg)) return -EAGAIN; skcipher = crypto_create_tfm(calg, &crypto_lskcipher_type); if (IS_ERR(skcipher)) { crypto_mod_put(calg); return PTR_ERR(skcipher); } *ctx = skcipher; tfm->exit = crypto_lskcipher_exit_tfm_sg; return 0; } int crypto_grab_lskcipher(struct crypto_lskcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_lskcipher_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_lskcipher); struct crypto_lskcipher *crypto_alloc_lskcipher(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_lskcipher_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_lskcipher); static int lskcipher_prepare_alg(struct lskcipher_alg *alg) { struct crypto_alg *base = &alg->co.base; int err; err = skcipher_prepare_alg_common(&alg->co); if (err) return err; if (alg->co.chunksize & (alg->co.chunksize - 1)) return -EINVAL; base->cra_type = &crypto_lskcipher_type; base->cra_flags |= CRYPTO_ALG_TYPE_LSKCIPHER; return 0; } int crypto_register_lskcipher(struct lskcipher_alg *alg) { struct crypto_alg *base = &alg->co.base; int err; err = lskcipher_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_lskcipher); void crypto_unregister_lskcipher(struct lskcipher_alg *alg) { crypto_unregister_alg(&alg->co.base); } EXPORT_SYMBOL_GPL(crypto_unregister_lskcipher); int crypto_register_lskciphers(struct lskcipher_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_lskcipher(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_lskcipher(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_lskciphers); void crypto_unregister_lskciphers(struct lskcipher_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_lskcipher(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_lskciphers); int lskcipher_register_instance(struct crypto_template *tmpl, struct lskcipher_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = lskcipher_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, lskcipher_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(lskcipher_register_instance); static int lskcipher_setkey_simple(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen) { struct crypto_lskcipher *cipher = lskcipher_cipher_simple(tfm); crypto_lskcipher_clear_flags(cipher, CRYPTO_TFM_REQ_MASK); crypto_lskcipher_set_flags(cipher, crypto_lskcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); return crypto_lskcipher_setkey(cipher, key, keylen); } static int lskcipher_init_tfm_simple(struct crypto_lskcipher *tfm) { struct lskcipher_instance *inst = lskcipher_alg_instance(tfm); struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm); struct crypto_lskcipher_spawn *spawn; struct crypto_lskcipher *cipher; spawn = lskcipher_instance_ctx(inst); cipher = crypto_spawn_lskcipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); *ctx = cipher; return 0; } static void lskcipher_exit_tfm_simple(struct crypto_lskcipher *tfm) { struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm); crypto_free_lskcipher(*ctx); } static void lskcipher_free_instance_simple(struct lskcipher_instance *inst) { crypto_drop_lskcipher(lskcipher_instance_ctx(inst)); kfree(inst); } /** * lskcipher_alloc_instance_simple - allocate instance of simple block cipher * * Allocate an lskcipher_instance for a simple block cipher mode of operation, * e.g. cbc or ecb. The instance context will have just a single crypto_spawn, * that for the underlying cipher. The {min,max}_keysize, ivsize, blocksize, * alignmask, and priority are set from the underlying cipher but can be * overridden if needed. The tfm context defaults to * struct crypto_lskcipher *, and default ->setkey(), ->init(), and * ->exit() methods are installed. * * @tmpl: the template being instantiated * @tb: the template parameters * * Return: a pointer to the new instance, or an ERR_PTR(). The caller still * needs to register the instance. */ struct lskcipher_instance *lskcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; struct lskcipher_instance *inst; struct crypto_lskcipher_spawn *spawn; char ecb_name[CRYPTO_MAX_ALG_NAME]; struct lskcipher_alg *cipher_alg; const char *cipher_name; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_LSKCIPHER, &mask); if (err) return ERR_PTR(err); cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) return ERR_CAST(cipher_name); inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return ERR_PTR(-ENOMEM); spawn = lskcipher_instance_ctx(inst); err = crypto_grab_lskcipher(spawn, lskcipher_crypto_instance(inst), cipher_name, 0, mask); ecb_name[0] = 0; if (err == -ENOENT && !!memcmp(tmpl->name, "ecb", 4)) { err = -ENAMETOOLONG; if (snprintf(ecb_name, CRYPTO_MAX_ALG_NAME, "ecb(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; err = crypto_grab_lskcipher(spawn, lskcipher_crypto_instance(inst), ecb_name, 0, mask); } if (err) goto err_free_inst; cipher_alg = crypto_lskcipher_spawn_alg(spawn); err = crypto_inst_setname(lskcipher_crypto_instance(inst), tmpl->name, &cipher_alg->co.base); if (err) goto err_free_inst; if (ecb_name[0]) { int len; err = -EINVAL; len = strscpy(ecb_name, &cipher_alg->co.base.cra_name[4], sizeof(ecb_name)); if (len < 2) goto err_free_inst; if (ecb_name[len - 1] != ')') goto err_free_inst; ecb_name[len - 1] = 0; err = -ENAMETOOLONG; if (snprintf(inst->alg.co.base.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", tmpl->name, ecb_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; if (strcmp(ecb_name, cipher_name) && snprintf(inst->alg.co.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", tmpl->name, cipher_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; } else { /* Don't allow nesting. */ err = -ELOOP; if ((cipher_alg->co.base.cra_flags & CRYPTO_ALG_INSTANCE)) goto err_free_inst; } err = -EINVAL; if (cipher_alg->co.ivsize) goto err_free_inst; inst->free = lskcipher_free_instance_simple; /* Default algorithm properties, can be overridden */ inst->alg.co.base.cra_blocksize = cipher_alg->co.base.cra_blocksize; inst->alg.co.base.cra_alignmask = cipher_alg->co.base.cra_alignmask; inst->alg.co.base.cra_priority = cipher_alg->co.base.cra_priority; inst->alg.co.min_keysize = cipher_alg->co.min_keysize; inst->alg.co.max_keysize = cipher_alg->co.max_keysize; inst->alg.co.ivsize = cipher_alg->co.base.cra_blocksize; inst->alg.co.statesize = cipher_alg->co.statesize; /* Use struct crypto_lskcipher * by default, can be overridden */ inst->alg.co.base.cra_ctxsize = sizeof(struct crypto_lskcipher *); inst->alg.setkey = lskcipher_setkey_simple; inst->alg.init = lskcipher_init_tfm_simple; inst->alg.exit = lskcipher_exit_tfm_simple; return inst; err_free_inst: lskcipher_free_instance_simple(inst); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(lskcipher_alloc_instance_simple); |
| 1399 8 8 2600 1919 1924 1217 1213 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 116 117 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/freezer.c - Function to freeze a process * * Originally from kernel/power/process.c */ #include <linux/interrupt.h> #include <linux/suspend.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/freezer.h> #include <linux/kthread.h> /* total number of freezing conditions in effect */ DEFINE_STATIC_KEY_FALSE(freezer_active); EXPORT_SYMBOL(freezer_active); /* * indicate whether PM freezing is in effect, protected by * system_transition_mutex */ bool pm_freezing; bool pm_nosig_freezing; /* protects freezing and frozen transitions */ static DEFINE_SPINLOCK(freezer_lock); /** * freezing_slow_path - slow path for testing whether a task needs to be frozen * @p: task to be tested * * This function is called by freezing() if freezer_active isn't zero * and tests whether @p needs to enter and stay in frozen state. Can be * called under any context. The freezers are responsible for ensuring the * target tasks see the updated state. */ bool freezing_slow_path(struct task_struct *p) { if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; if (test_tsk_thread_flag(p, TIF_MEMDIE)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) return true; if (pm_freezing && !(p->flags & PF_KTHREAD)) return true; return false; } EXPORT_SYMBOL(freezing_slow_path); bool frozen(struct task_struct *p) { return READ_ONCE(p->__state) & TASK_FROZEN; } /* Refrigerator is place where frozen processes are stored :-). */ bool __refrigerator(bool check_kthr_stop) { unsigned int state = get_current_state(); bool was_frozen = false; pr_debug("%s entered refrigerator\n", current->comm); WARN_ON_ONCE(state && !(state & TASK_NORMAL)); for (;;) { bool freeze; raw_spin_lock_irq(¤t->pi_lock); WRITE_ONCE(current->__state, TASK_FROZEN); /* unstale saved_state so that __thaw_task() will wake us up */ current->saved_state = TASK_RUNNING; raw_spin_unlock_irq(¤t->pi_lock); spin_lock_irq(&freezer_lock); freeze = freezing(current) && !(check_kthr_stop && kthread_should_stop()); spin_unlock_irq(&freezer_lock); if (!freeze) break; was_frozen = true; schedule(); } __set_current_state(TASK_RUNNING); pr_debug("%s left refrigerator\n", current->comm); return was_frozen; } EXPORT_SYMBOL(__refrigerator); static void fake_signal_wake_up(struct task_struct *p) { unsigned long flags; if (lock_task_sighand(p, &flags)) { signal_wake_up(p, 0); unlock_task_sighand(p, &flags); } } static int __set_task_frozen(struct task_struct *p, void *arg) { unsigned int state = READ_ONCE(p->__state); /* * Allow freezing the sched_delayed tasks; they will not execute until * ttwu() fixes them up, so it is safe to swap their state now, instead * of waiting for them to get fully dequeued. */ if (task_is_runnable(p)) return 0; if (p != current && task_curr(p)) return 0; if (!(state & (TASK_FREEZABLE | __TASK_STOPPED | __TASK_TRACED))) return 0; /* * Only TASK_NORMAL can be augmented with TASK_FREEZABLE, since they * can suffer spurious wakeups. */ if (state & TASK_FREEZABLE) WARN_ON_ONCE(!(state & TASK_NORMAL)); #ifdef CONFIG_LOCKDEP /* * It's dangerous to freeze with locks held; there be dragons there. */ if (!(state & __TASK_FREEZABLE_UNSAFE)) WARN_ON_ONCE(debug_locks && p->lockdep_depth); #endif p->saved_state = p->__state; WRITE_ONCE(p->__state, TASK_FROZEN); return TASK_FROZEN; } static bool __freeze_task(struct task_struct *p) { /* TASK_FREEZABLE|TASK_STOPPED|TASK_TRACED -> TASK_FROZEN */ return task_call_func(p, __set_task_frozen, NULL); } /** * freeze_task - send a freeze request to given task * @p: task to send the request to * * If @p is freezing, the freeze request is sent either by sending a fake * signal (if it's not a kernel thread) or waking it up (if it's a kernel * thread). * * RETURNS: * %false, if @p is not freezing or already frozen; %true, otherwise */ bool freeze_task(struct task_struct *p) { unsigned long flags; spin_lock_irqsave(&freezer_lock, flags); if (!freezing(p) || frozen(p) || __freeze_task(p)) { spin_unlock_irqrestore(&freezer_lock, flags); return false; } if (!(p->flags & PF_KTHREAD)) fake_signal_wake_up(p); else wake_up_state(p, TASK_NORMAL); spin_unlock_irqrestore(&freezer_lock, flags); return true; } /* * Restore the saved_state before the task entered freezer. For typical task * in the __refrigerator(), saved_state == TASK_RUNNING so nothing happens * here. For tasks which were TASK_NORMAL | TASK_FREEZABLE, their initial state * is restored unless they got an expected wakeup (see ttwu_state_match()). * Returns 1 if the task state was restored. */ static int __restore_freezer_state(struct task_struct *p, void *arg) { unsigned int state = p->saved_state; if (state != TASK_RUNNING) { WRITE_ONCE(p->__state, state); p->saved_state = TASK_RUNNING; return 1; } return 0; } void __thaw_task(struct task_struct *p) { unsigned long flags; spin_lock_irqsave(&freezer_lock, flags); if (WARN_ON_ONCE(freezing(p))) goto unlock; if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL)) goto unlock; wake_up_state(p, TASK_FROZEN); unlock: spin_unlock_irqrestore(&freezer_lock, flags); } /** * set_freezable - make %current freezable * * Mark %current freezable and enter refrigerator if necessary. */ bool set_freezable(void) { might_sleep(); /* * Modify flags while holding freezer_lock. This ensures the * freezer notices that we aren't frozen yet or the freezing * condition is visible to try_to_freeze() below. */ spin_lock_irq(&freezer_lock); current->flags &= ~PF_NOFREEZE; spin_unlock_irq(&freezer_lock); return try_to_freeze(); } EXPORT_SYMBOL(set_freezable); |
| 2 154 60 106 106 262 47 227 227 545 544 115 84 114 114 255 255 104 152 167 167 82 85 40 18 1 36 2540 926 2016 158 10 10 1 1 168 10 9 187 187 1 181 1863 1862 2 47 1802 545 1384 39 1383 1384 25 1664 263 2 2 13 13 13 14 668 6 20 20 9 630 30 2 4 35 1 3 2 3 2 3 2 19 15 1 1 13 18 1 2 1 1 14 5 1 4 38 1 1 1 1 1 1 32 260 261 183 183 183 84 84 84 545 4 7 11 4 528 106 2 1 1 1 1 1 1 1 1 1 2 1 3 1 1 1 1 2 1 2 1 4 3 73 4 1 17 38 22 6 1 15 21 22 1 1 18 10 8 2 19 10 8 1 405 403 403 2 13 12 12 2 6259 6263 6265 1770 3303 1546 2384 84 56 115 401 1 1 400 10 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/bpf_perf_event.h> #include <linux/btf.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/error-injection.h> #include <linux/btf_ids.h> #include <linux/bpf_lsm.h> #include <linux/fprobe.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/key.h> #include <linux/verification.h> #include <linux/namei.h> #include <net/bpf_sk_storage.h> #include <uapi/linux/bpf.h> #include <uapi/linux/btf.h> #include <asm/tlb.h> #include "trace_probe.h" #include "trace.h" #define CREATE_TRACE_POINTS #include "bpf_trace.h" #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) #define MAX_UPROBE_MULTI_CNT (1U << 20) #define MAX_KPROBE_MULTI_CNT (1U << 20) #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; struct list_head list; }; static LIST_HEAD(bpf_trace_modules); static DEFINE_MUTEX(bpf_module_mutex); static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { struct bpf_raw_event_map *btp, *ret = NULL; struct bpf_trace_module *btm; unsigned int i; mutex_lock(&bpf_module_mutex); list_for_each_entry(btm, &bpf_trace_modules, list) { for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { btp = &btm->module->bpf_raw_events[i]; if (!strcmp(btp->tp->name, name)) { if (try_module_get(btm->module)) ret = btp; goto out; } } } out: mutex_unlock(&bpf_module_mutex); return ret; } #else static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { return NULL; } #endif /* CONFIG_MODULES */ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id); static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx); /** * trace_call_bpf - invoke BPF program * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ rcu_read_lock(); bpf_prog_inc_misses_counters(rcu_dereference(call->prog_array)); rcu_read_unlock(); ret = 0; goto out; } /* * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is * a heuristic to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual * proper rcu_dereference() under RCU lock. * If it turns out that prog_array is NULL then, we bail out. * For the opposite, if the bpf_prog_array_valid() fetched pointer * was NULL, you'll skip the prog_array with the risk of missing * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ rcu_read_lock(); ret = bpf_prog_run_array(rcu_dereference(call->prog_array), ctx, bpf_prog_run); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); return ret; } #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { regs_set_return_value(regs, rc); override_function_with_return(regs); return 0; } static const struct bpf_func_proto bpf_override_return_proto = { .func = bpf_override_return, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; #endif static __always_inline int bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; ret = copy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_proto = { .func = bpf_probe_read_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_user_str_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; /* * NB: We rely on strncpy_from_user() not copying junk past the NUL * terminator into `dst`. * * strncpy_from_user() does long-sized strides in the fast path. If the * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, * then there could be junk after the NUL in `dst`. If user takes `dst` * and keys a hash map with it, then semantically identical strings can * occupy multiple entries in the map. */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_str_proto = { .func = bpf_probe_read_user_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_proto = { .func = bpf_probe_read_kernel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the * entire buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read_*() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { .func = bpf_probe_read_kernel_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_proto = { .func = bpf_probe_read_compat, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_str_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. * * nmi_uaccess_okay() ensures the probe is not run in an interim * state, when the task or mm are switched. This is specifically * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; return copy_to_user_nofault(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret; ret = bpf_bprintf_prepare(fmt, fmt_size, args, MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; static void __set_printk_clr_event(struct work_struct *work) { /* * This program might be calling bpf_trace_printk, * so enable the associated bpf_trace/bpf_trace_printk event. * Repeat this each time as it is possible a user has * disabled bpf_trace_printk events. By loading a program * calling bpf_trace_printk() however the user has expressed * the intent to see such events. */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); } static DECLARE_WORK(set_printk_work, __set_printk_clr_event); const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { schedule_work(&set_printk_work); return &bpf_trace_printk_proto; } BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) { schedule_work(&set_printk_work); return &bpf_trace_vprintk_proto; } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, }; int err, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (err < 0) return err; seq_bprintf(m, fmt, data.bin_args); bpf_bprintf_cleanup(&data); return seq_has_overflowed(m) ? -EOVERFLOW : 0; } BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file) static const struct bpf_func_proto bpf_seq_printf_proto = { .func = bpf_seq_printf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) { return seq_write(m, data, len) ? -EOVERFLOW : 0; } static const struct bpf_func_proto bpf_seq_write_proto = { .func = bpf_seq_write, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr, u32, btf_ptr_size, u64, flags) { const struct btf *btf; s32 btf_id; int ret; ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); if (ret) return ret; return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags); } static const struct bpf_func_proto bpf_seq_printf_btf_proto = { .func = bpf_seq_printf_btf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static __always_inline int get_map_perf_counter(struct bpf_map *map, u64 flags, u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; return perf_event_read_local(ee->event, value, enabled, running); } BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) { u64 value = 0; int err; err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi */ if (err) return err; return value; } const struct bpf_func_proto bpf_perf_event_read_proto = { .func = bpf_perf_event_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .func = bpf_perf_event_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void) { return &bpf_perf_event_read_value_proto; } static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_raw_record *raw, struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; struct perf_event *event; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; perf_sample_save_raw_data(sd, event, raw); return perf_event_output(event, sd, regs); } /* * Support executing tracepoints in normal, irq, and nmi context that each call * bpf_perf_event_output */ struct bpf_trace_sample_data { struct perf_sample_data sds[3]; }; static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds); static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; struct perf_sample_data *sd; int nest_level, err; preempt_disable(); sds = this_cpu_ptr(&bpf_trace_sds); nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; goto out; } sd = &sds->sds[nest_level - 1]; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) { err = -EINVAL; goto out; } perf_sample_data_init(sd, 0, 0); err = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_trace_nest_level); preempt_enable(); return err; } static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static DEFINE_PER_CPU(int, bpf_event_output_nest_level); struct bpf_nested_pt_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs); static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, .data = ctx, }; struct perf_raw_record raw = { .frag = { { .next = ctx_size ? &frag : NULL, }, .size = meta_size, .data = meta, }, }; struct perf_sample_data *sd; struct pt_regs *regs; int nest_level; u64 ret; preempt_disable(); nest_level = this_cpu_inc_return(bpf_event_output_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; } sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]); regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]); perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); ret = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_event_output_nest_level); preempt_enable(); return ret; } BPF_CALL_0(bpf_get_current_task) { return (long) current; } const struct bpf_func_proto bpf_get_current_task_proto = { .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_current_task_btf) { return (unsigned long) current; } const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID_TRUSTED, .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task) { return (unsigned long) task_pt_regs(task); } BTF_ID_LIST(bpf_task_pt_regs_ids) BTF_ID(struct, pt_regs) const struct bpf_func_proto bpf_task_pt_regs_proto = { .func = bpf_task_pt_regs, .gpl_only = true, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &bpf_task_pt_regs_ids[0], }; struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; u32 sig; enum pid_type type; bool has_siginfo; struct kernel_siginfo info; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); static void do_bpf_send_signal(struct irq_work *entry) { struct send_signal_irq_work *work; struct kernel_siginfo *siginfo; work = container_of(entry, struct send_signal_irq_work, irq_work); siginfo = work->has_siginfo ? &work->info : SEND_SIG_PRIV; group_send_sig_info(work->sig, siginfo, work->task, work->type); put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struct *task, u64 value) { struct send_signal_irq_work *work = NULL; struct kernel_siginfo info; struct kernel_siginfo *siginfo; if (!task) { task = current; siginfo = SEND_SIG_PRIV; } else { clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; info.si_value.sival_ptr = (void *)(unsigned long)value; siginfo = &info; } /* Similar to bpf_probe_write_user, task needs to be * in a sound condition and kernel memory access be * permitted in order to send signal to the current * task. */ if (unlikely(task->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; /* Task should not be pid=1 to avoid kernel panic. */ if (unlikely(is_global_init(task))) return -EPERM; if (preempt_count() != 0 || irqs_disabled()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ if (unlikely(!valid_signal(sig))) return -EINVAL; work = this_cpu_ptr(&send_signal_work); if (irq_work_is_busy(&work->irq_work)) return -EBUSY; /* Add the current task, which is the target of sending signal, * to the irq_work. The current task may change when queued * irq works get executed. */ work->task = get_task_struct(task); work->has_siginfo = siginfo == &info; if (work->has_siginfo) copy_siginfo(&work->info, &info); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); return 0; } return group_send_sig_info(sig, siginfo, task, type); } BPF_CALL_1(bpf_send_signal, u32, sig) { return bpf_send_signal_common(sig, PIDTYPE_TGID, NULL, 0); } const struct bpf_func_proto bpf_send_signal_proto = { .func = bpf_send_signal, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_send_signal_thread, u32, sig) { return bpf_send_signal_common(sig, PIDTYPE_PID, NULL, 0); } const struct bpf_func_proto bpf_send_signal_thread_proto = { .func = bpf_send_signal_thread, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) { struct path copy; long len; char *p; if (!sz) return 0; /* * The path pointer is verified as trusted and safe to use, * but let's double check it's valid anyway to workaround * potentially broken verifier. */ len = copy_from_kernel_nofault(©, path, sizeof(*path)); if (len < 0) return len; p = d_path(©, buf, sz); if (IS_ERR(p)) { len = PTR_ERR(p); } else { len = buf + sz - p; memmove(buf, p, len); } return len; } BTF_SET_START(btf_allowlist_d_path) #ifdef CONFIG_SECURITY BTF_ID(func, security_file_permission) BTF_ID(func, security_inode_getattr) BTF_ID(func, security_file_open) #endif #ifdef CONFIG_SECURITY_PATH BTF_ID(func, security_path_truncate) #endif BTF_ID(func, vfs_truncate) BTF_ID(func, vfs_fallocate) BTF_ID(func, dentry_open) BTF_ID(func, vfs_getattr) BTF_ID(func, filp_close) BTF_SET_END(btf_allowlist_d_path) static bool bpf_d_path_allowed(const struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_ITER) return true; if (prog->type == BPF_PROG_TYPE_LSM) return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id); } BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path) static const struct bpf_func_proto bpf_d_path_proto = { .func = bpf_d_path, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_d_path_btf_ids[0], .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .allowed = bpf_d_path_allowed, }; #define BTF_F_ALL (BTF_F_COMPACT | BTF_F_NONAME | \ BTF_F_PTR_RAW | BTF_F_ZERO) static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id) { const struct btf_type *t; if (unlikely(flags & ~(BTF_F_ALL))) return -EINVAL; if (btf_ptr_size != sizeof(struct btf_ptr)) return -EINVAL; *btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(*btf)) return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; if (ptr->type_id > 0) *btf_id = ptr->type_id; else return -EINVAL; if (*btf_id > 0) t = btf_type_by_id(*btf, *btf_id); if (*btf_id <= 0 || !t) return -ENOENT; return 0; } BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr, u32, btf_ptr_size, u64, flags) { const struct btf *btf; s32 btf_id; int ret; ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); if (ret) return ret; return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size, flags); } const struct bpf_func_proto bpf_snprintf_btf_proto = { .func = bpf_snprintf_btf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { .func = bpf_get_func_ip_tracing, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline unsigned long get_entry_ip(unsigned long fentry_ip) { #ifdef CONFIG_X86_KERNEL_IBT if (is_endbr((void *)(fentry_ip - ENDBR_INSN_SIZE))) fentry_ip -= ENDBR_INSN_SIZE; #endif return fentry_ip; } BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs) { struct bpf_trace_run_ctx *run_ctx __maybe_unused; struct kprobe *kp; #ifdef CONFIG_UPROBES run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); if (run_ctx->is_uprobe) return ((struct uprobe_dispatch_data *)current->utask->vaddr)->bp_addr; #endif kp = kprobe_running(); if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY)) return 0; return get_entry_ip((uintptr_t)kp->addr); } static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = { .func = bpf_get_func_ip_kprobe, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs) { return bpf_kprobe_multi_entry_ip(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = { .func = bpf_get_func_ip_kprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs) { return bpf_kprobe_multi_cookie(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = { .func = bpf_get_attach_cookie_kprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_func_ip_uprobe_multi, struct pt_regs *, regs) { return bpf_uprobe_multi_entry_ip(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_func_ip_proto_uprobe_multi = { .func = bpf_get_func_ip_uprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_uprobe_multi, struct pt_regs *, regs) { return bpf_uprobe_multi_cookie(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_attach_cookie_proto_umulti = { .func = bpf_get_attach_cookie_uprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); return run_ctx->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_trace = { .func = bpf_get_attach_cookie_trace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_pe, struct bpf_perf_event_data_kern *, ctx) { return ctx->event->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .func = bpf_get_attach_cookie_pe, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_tracing, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); return run_ctx->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = { .func = bpf_get_attach_cookie_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) { static const u32 br_entry_size = sizeof(struct perf_branch_entry); u32 entry_cnt = size / br_entry_size; entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); if (unlikely(flags)) return -EINVAL; if (!entry_cnt) return -ENOENT; return entry_cnt * br_entry_size; } const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .func = bpf_get_branch_snapshot, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) { /* This helper call is inlined by verifier. */ u64 nr_args = ((u64 *)ctx)[-1]; if ((u64) n >= nr_args) return -EINVAL; *value = ((u64 *)ctx)[n]; return 0; } static const struct bpf_func_proto bpf_get_func_arg_proto = { .func = get_func_arg, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u64), }; BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) { /* This helper call is inlined by verifier. */ u64 nr_args = ((u64 *)ctx)[-1]; *value = ((u64 *)ctx)[nr_args]; return 0; } static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg2_size = sizeof(u64), }; BPF_CALL_1(get_func_arg_cnt, void *, ctx) { /* This helper call is inlined by verifier. */ return ((u64 *)ctx)[-1]; } static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { .func = get_func_arg_cnt, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #ifdef CONFIG_KEYS __bpf_kfunc_start_defs(); /** * bpf_lookup_user_key - lookup a key by its serial * @serial: key handle serial number * @flags: lookup-specific flags * * Search a key with a given *serial* and the provided *flags*. * If found, increment the reference count of the key by one, and * return it in the bpf_key structure. * * The bpf_key structure must be passed to bpf_key_put() when done * with it, so that the key reference count is decremented and the * bpf_key structure is freed. * * Permission checks are deferred to the time the key is used by * one of the available key-specific kfuncs. * * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested * special keyring (e.g. session keyring), if it doesn't yet exist. * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting * for the key construction, and to retrieve uninstantiated keys (keys * without data attached to them). * * Return: a bpf_key pointer with a valid key pointer if the key is found, a * NULL pointer otherwise. */ __bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) { key_ref_t key_ref; struct bpf_key *bkey; if (flags & ~KEY_LOOKUP_ALL) return NULL; /* * Permission check is deferred until the key is used, as the * intent of the caller is unknown here. */ key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK); if (IS_ERR(key_ref)) return NULL; bkey = kmalloc(sizeof(*bkey), GFP_KERNEL); if (!bkey) { key_put(key_ref_to_ptr(key_ref)); return NULL; } bkey->key = key_ref_to_ptr(key_ref); bkey->has_ref = true; return bkey; } /** * bpf_lookup_system_key - lookup a key by a system-defined ID * @id: key ID * * Obtain a bpf_key structure with a key pointer set to the passed key ID. * The key pointer is marked as invalid, to prevent bpf_key_put() from * attempting to decrement the key reference count on that pointer. The key * pointer set in such way is currently understood only by * verify_pkcs7_signature(). * * Set *id* to one of the values defined in include/linux/verification.h: * 0 for the primary keyring (immutable keyring of system keys); * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring * (where keys can be added only if they are vouched for by existing keys * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform * keyring (primarily used by the integrity subsystem to verify a kexec'ed * kerned image and, possibly, the initramfs signature). * * Return: a bpf_key pointer with an invalid key pointer set from the * pre-determined ID on success, a NULL pointer otherwise */ __bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id) { struct bpf_key *bkey; if (system_keyring_id_check(id) < 0) return NULL; bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC); if (!bkey) return NULL; bkey->key = (struct key *)(unsigned long)id; bkey->has_ref = false; return bkey; } /** * bpf_key_put - decrement key reference count if key is valid and free bpf_key * @bkey: bpf_key structure * * Decrement the reference count of the key inside *bkey*, if the pointer * is valid, and free *bkey*. */ __bpf_kfunc void bpf_key_put(struct bpf_key *bkey) { if (bkey->has_ref) key_put(bkey->key); kfree(bkey); } #ifdef CONFIG_SYSTEM_DATA_VERIFICATION /** * bpf_verify_pkcs7_signature - verify a PKCS#7 signature * @data_p: data to verify * @sig_p: signature of the data * @trusted_keyring: keyring with keys trusted for signature verification * * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr* * with keys in a keyring referenced by *trusted_keyring*. * * Return: 0 on success, a negative value on error. */ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, struct bpf_dynptr *sig_p, struct bpf_key *trusted_keyring) { struct bpf_dynptr_kern *data_ptr = (struct bpf_dynptr_kern *)data_p; struct bpf_dynptr_kern *sig_ptr = (struct bpf_dynptr_kern *)sig_p; const void *data, *sig; u32 data_len, sig_len; int ret; if (trusted_keyring->has_ref) { /* * Do the permission check deferred in bpf_lookup_user_key(). * See bpf_lookup_user_key() for more details. * * A call to key_task_permission() here would be redundant, as * it is already done by keyring_search() called by * find_asymmetric_key(). */ ret = key_validate(trusted_keyring->key); if (ret < 0) return ret; } data_len = __bpf_dynptr_size(data_ptr); data = __bpf_dynptr_data(data_ptr, data_len); sig_len = __bpf_dynptr_size(sig_ptr); sig = __bpf_dynptr_data(sig_ptr, sig_len); return verify_pkcs7_signature(data, data_len, sig, sig_len, trusted_keyring->key, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); } #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ __bpf_kfunc_end_defs(); BTF_KFUNCS_START(key_sig_kfunc_set) BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE) #ifdef CONFIG_SYSTEM_DATA_VERIFICATION BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE) #endif BTF_KFUNCS_END(key_sig_kfunc_set) static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = { .owner = THIS_MODULE, .set = &key_sig_kfunc_set, }; static int __init bpf_key_sig_kfuncs_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_key_sig_kfunc_set); } late_initcall(bpf_key_sig_kfuncs_init); #endif /* CONFIG_KEYS */ static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; switch (func_id) { case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; default: break; } func_proto = bpf_base_func_proto(func_id, prog); if (func_proto) return func_proto; if (!bpf_token_capable(prog->aux->token, CAP_SYS_ADMIN)) return NULL; switch (func_id) { case BPF_FUNC_probe_write_user: return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? NULL : &bpf_probe_write_user_proto; default: return NULL; } } static bool is_kprobe_multi(const struct bpf_prog *prog) { return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI || prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; } static inline bool is_kprobe_session(const struct bpf_prog *prog) { return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; } static inline bool is_uprobe_multi(const struct bpf_prog *prog) { return prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI || prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; } static inline bool is_uprobe_session(const struct bpf_prog *prog) { return prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; } static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: return prog->sleepable ? &bpf_get_stack_sleepable_proto : &bpf_get_stack_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: if (is_kprobe_multi(prog)) return &bpf_get_func_ip_proto_kprobe_multi; if (is_uprobe_multi(prog)) return &bpf_get_func_ip_proto_uprobe_multi; return &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: if (is_kprobe_multi(prog)) return &bpf_get_attach_cookie_proto_kmulti; if (is_uprobe_multi(prog)) return &bpf_get_attach_cookie_proto_umulti; return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; /* * Assertion for 32 bit to make sure last 8 byte access * (BPF_DW) to the last 4 byte member is disallowed. */ if (off + size > sizeof(struct pt_regs)) return false; return true; } const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; const struct bpf_prog_ops kprobe_prog_ops = { }; BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * r1 points to perf tracepoint buffer where first 8 bytes are hidden * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it * from there and call the same bpf_perf_event_output() helper inline. */ return ____bpf_perf_event_output(regs, map, flags, data, size); } static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .func = bpf_perf_event_output_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * Same comment as in bpf_perf_event_output_tp(), only that this time * the other helper's function body cannot be inlined due to being * external, thus we need to call raw helper function. */ return bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); } static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .func = bpf_get_stackid_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; return bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); } static const struct bpf_func_proto bpf_get_stack_proto_tp = { .func = bpf_get_stack_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; case BPF_FUNC_get_attach_cookie: return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); return true; } const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; const struct bpf_prog_ops tracepoint_prog_ops = { }; BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { static const u32 br_entry_size = sizeof(struct perf_branch_entry); struct perf_branch_stack *br_stack = ctx->data->br_stack; u32 to_copy; if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE)) return -EINVAL; if (unlikely(!(ctx->data->sample_flags & PERF_SAMPLE_BRANCH_STACK))) return -ENOENT; if (unlikely(!br_stack)) return -ENOENT; if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) return br_stack->nr * br_entry_size; if (!buf || (size % br_entry_size != 0)) return -EINVAL; to_copy = min_t(u32, br_stack->nr * br_entry_size, size); memcpy(buf, br_stack->entries, to_copy); return to_copy; } static const struct bpf_func_proto bpf_read_branch_records_proto = { .func = bpf_read_branch_records, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM_OR_NULL, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_pe; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_pe; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; case BPF_FUNC_read_branch_records: return &bpf_read_branch_records_proto; case BPF_FUNC_get_attach_cookie: return &bpf_get_attach_cookie_proto_pe; default: return bpf_tracing_func_proto(func_id, prog); } } /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack. * * Since raw tracepoints run despite bpf_prog_active, support concurrent usage * in normal, irq, and nmi context. */ struct bpf_raw_tp_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs); static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level); static struct pt_regs *get_bpf_raw_tp_regs(void) { struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs); int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level); if (nest_level > ARRAY_SIZE(tp_regs->regs)) { this_cpu_dec(bpf_raw_tp_nest_level); return ERR_PTR(-EBUSY); } return &tp_regs->regs[nest_level - 1]; } static void put_bpf_raw_tp_regs(void) { this_cpu_dec(bpf_raw_tp_nest_level); } BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = ____bpf_perf_event_output(regs, map, flags, data, size); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .func = bpf_perf_event_output_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */ ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .func = bpf_get_stackid_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .func = bpf_get_stack_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; case BPF_FUNC_get_attach_cookie: return &bpf_get_attach_cookie_proto_tracing; default: return bpf_tracing_func_proto(func_id, prog); } } const struct bpf_func_proto * tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *fn; switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_skb_output: return &bpf_skb_output_proto; case BPF_FUNC_xdp_output: return &bpf_xdp_output_proto; case BPF_FUNC_skc_to_tcp6_sock: return &bpf_skc_to_tcp6_sock_proto; case BPF_FUNC_skc_to_tcp_sock: return &bpf_skc_to_tcp_sock_proto; case BPF_FUNC_skc_to_tcp_timewait_sock: return &bpf_skc_to_tcp_timewait_sock_proto; case BPF_FUNC_skc_to_tcp_request_sock: return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; case BPF_FUNC_skc_to_unix_sock: return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_skc_to_mptcp_sock: return &bpf_skc_to_mptcp_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_tracing_proto; case BPF_FUNC_sock_from_file: return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_printf_proto : NULL; case BPF_FUNC_seq_write: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_write_proto : NULL; case BPF_FUNC_seq_printf_btf: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_printf_btf_proto : NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; case BPF_FUNC_get_func_arg: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; case BPF_FUNC_get_func_ret: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; case BPF_FUNC_get_attach_cookie: if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) return &bpf_get_attach_cookie_proto_tracing; return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) fn = bpf_iter_get_func_proto(func_id, prog); return fn; } } static bool raw_tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_prog_ops = { #ifdef CONFIG_NET .test_run = bpf_prog_test_run_raw_tp, #endif }; const struct bpf_verifier_ops tracing_verifier_ops = { .get_func_proto = tracing_prog_func_proto, .is_valid_access = tracing_prog_is_valid_access, }; const struct bpf_prog_ops tracing_prog_ops = { .test_run = bpf_prog_test_run_tracing, }; static bool raw_tp_writable_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off == 0) { if (size != sizeof(u64) || type != BPF_READ) return false; info->reg_type = PTR_TO_TP_BUFFER; } return raw_tp_prog_is_valid_access(off, size, type, prog, info); } const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_writable_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_u64 = sizeof(u64); if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) { if (sizeof(unsigned long) != 4) return false; if (size != 8) return false; if (off % size != 4) return false; } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; case bpf_ctx_range(struct bpf_perf_event_data, addr): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; default: if (size != sizeof(long)) return false; } return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, period, 8, target_size)); break; case offsetof(struct bpf_perf_event_data, addr): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, addr, 8, target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, regs)); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg, si->off); break; } return insn - insn_buf; } const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; const struct bpf_prog_ops perf_event_prog_ops = { }; static DEFINE_MUTEX(bpf_event_mutex); #define BPF_TRACE_MAX_PROGS 64 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret = -EEXIST; /* * Kprobe override only works if they are on the function entry, * and only if they are on the opt-in list. */ if (prog->kprobe_override && (!trace_kprobe_on_func_entry(event->tp_event) || !trace_kprobe_error_injectable(event->tp_event))) return -EINVAL; mutex_lock(&bpf_event_mutex); if (event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (old_array && bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { ret = -E2BIG; goto unlock; } ret = bpf_prog_array_copy(old_array, NULL, prog, bpf_cookie, &new_array); if (ret < 0) goto unlock; /* set the new array to event->tp_event and set event->prog */ event->prog = prog; event->bpf_cookie = bpf_cookie; rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free_sleepable(old_array); unlock: mutex_unlock(&bpf_event_mutex); return ret; } void perf_event_detach_bpf_prog(struct perf_event *event) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; struct bpf_prog *prog = NULL; int ret; mutex_lock(&bpf_event_mutex); if (!event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (!old_array) goto put; ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free_sleepable(old_array); } put: prog = event->prog; event->prog = NULL; unlock: mutex_unlock(&bpf_event_mutex); if (prog) { /* * It could be that the bpf_prog is not sleepable (and will be freed * via normal RCU), but is called from a point that supports sleepable * programs and uses tasks-trace-RCU. */ synchronize_rcu_tasks_trace(); bpf_prog_put(prog); } } int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; struct bpf_prog_array *progs; u32 *ids, prog_cnt, ids_len; int ret; if (!perfmon_capable()) return -EPERM; if (event->attr.type != PERF_TYPE_TRACEPOINT) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; ids_len = query.ids_len; if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; /* * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which * is required when user only wants to check for uquery->prog_cnt. * There is no need to check for it since the case is handled * gracefully in bpf_prog_array_copy_info. */ mutex_lock(&bpf_event_mutex); progs = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt); mutex_unlock(&bpf_event_mutex); if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) ret = -EFAULT; kfree(ids); return ret; } extern struct bpf_raw_event_map __start__bpf_raw_tp[]; extern struct bpf_raw_event_map __stop__bpf_raw_tp[]; struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { struct bpf_raw_event_map *btp = __start__bpf_raw_tp; for (; btp < __stop__bpf_raw_tp; btp++) { if (!strcmp(btp->tp->name, name)) return btp; } return bpf_get_raw_tracepoint_module(name); } void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { struct module *mod; guard(rcu)(); mod = __module_address((unsigned long)btp); module_put(mod); } static __always_inline void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args) { struct bpf_prog *prog = link->link.prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); goto out; } run_ctx.bpf_cookie = link->cookie; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); rcu_read_lock(); (void) bpf_prog_run(prog, args); rcu_read_unlock(); bpf_reset_run_ctx(old_run_ctx); out: this_cpu_dec(*(prog->active)); } #define UNPACK(...) __VA_ARGS__ #define REPEAT_1(FN, DL, X, ...) FN(X) #define REPEAT_2(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__) #define REPEAT_3(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__) #define REPEAT_4(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__) #define REPEAT_5(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__) #define REPEAT_6(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__) #define REPEAT_7(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__) #define REPEAT_8(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__) #define REPEAT_9(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__) #define REPEAT_10(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__) #define REPEAT_11(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__) #define REPEAT_12(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__) #define REPEAT(X, FN, DL, ...) REPEAT_##X(FN, DL, __VA_ARGS__) #define SARG(X) u64 arg##X #define COPY(X) args[X] = arg##X #define __DL_COM (,) #define __DL_SEM (;) #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ void bpf_trace_run##x(struct bpf_raw_tp_link *link, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ __bpf_trace_run(link, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); BPF_TRACE_DEFN_x(2); BPF_TRACE_DEFN_x(3); BPF_TRACE_DEFN_x(4); BPF_TRACE_DEFN_x(5); BPF_TRACE_DEFN_x(6); BPF_TRACE_DEFN_x(7); BPF_TRACE_DEFN_x(8); BPF_TRACE_DEFN_x(9); BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { struct tracepoint *tp = btp->tp; struct bpf_prog *prog = link->link.prog; /* * check that program doesn't access arguments beyond what's * available in this tracepoint */ if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, link); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, link); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr, unsigned long *missed) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; int flags, err = 0; prog = event->prog; if (!prog) return -ENOENT; /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) return -EOPNOTSUPP; *prog_id = prog->aux->id; flags = event->tp_event->flags; is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; is_syscall_tp = is_syscall_trace_event(event->tp_event); if (is_tracepoint || is_syscall_tp) { *buf = is_tracepoint ? event->tp_event->tp->name : event->tp_event->name; /* We allow NULL pointer for tracepoint */ if (fd_type) *fd_type = BPF_FD_TYPE_TRACEPOINT; if (probe_offset) *probe_offset = 0x0; if (probe_addr) *probe_addr = 0x0; } else { /* kprobe/uprobe */ err = -EOPNOTSUPP; #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, probe_offset, probe_addr, missed, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } return err; } static int __init send_signal_irq_work_init(void) { int cpu; struct send_signal_irq_work *work; for_each_possible_cpu(cpu) { work = per_cpu_ptr(&send_signal_work, cpu); init_irq_work(&work->irq_work, do_bpf_send_signal); } return 0; } subsys_initcall(send_signal_irq_work_init); #ifdef CONFIG_MODULES static int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) { struct bpf_trace_module *btm, *tmp; struct module *mod = module; int ret = 0; if (mod->num_bpf_raw_events == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) goto out; mutex_lock(&bpf_module_mutex); switch (op) { case MODULE_STATE_COMING: btm = kzalloc(sizeof(*btm), GFP_KERNEL); if (btm) { btm->module = module; list_add(&btm->list, &bpf_trace_modules); } else { ret = -ENOMEM; } break; case MODULE_STATE_GOING: list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) { if (btm->module == module) { list_del(&btm->list); kfree(btm); break; } } break; } mutex_unlock(&bpf_module_mutex); out: return notifier_from_errno(ret); } static struct notifier_block bpf_module_nb = { .notifier_call = bpf_event_notify, }; static int __init bpf_event_init(void) { register_module_notifier(&bpf_module_nb); return 0; } fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ struct bpf_session_run_ctx { struct bpf_run_ctx run_ctx; bool is_return; void *data; }; #ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; unsigned long *addrs; u64 *cookies; u32 cnt; u32 mods_cnt; struct module **mods; u32 flags; }; struct bpf_kprobe_multi_run_ctx { struct bpf_session_run_ctx session_ctx; struct bpf_kprobe_multi_link *link; unsigned long entry_ip; }; struct user_syms { const char **syms; char *buf; }; #ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); #define bpf_kprobe_multi_pt_regs_ptr() this_cpu_ptr(&bpf_kprobe_multi_pt_regs) #else #define bpf_kprobe_multi_pt_regs_ptr() (NULL) #endif static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip) { unsigned long ip = ftrace_get_symaddr(fentry_ip); return ip ? : fentry_ip; } static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; const char **syms = NULL; char *buf = NULL, *p; int err = -ENOMEM; unsigned int i; syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL); if (!syms) goto error; buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL); if (!buf) goto error; for (p = buf, i = 0; i < cnt; i++) { if (__get_user(usymbol, usyms + i)) { err = -EFAULT; goto error; } err = strncpy_from_user(p, (const char __user *) usymbol, KSYM_NAME_LEN); if (err == KSYM_NAME_LEN) err = -E2BIG; if (err < 0) goto error; syms[i] = p; p += err + 1; } us->syms = syms; us->buf = buf; return 0; error: if (err) { kvfree(syms); kvfree(buf); } return err; } static void kprobe_multi_put_modules(struct module **mods, u32 cnt) { u32 i; for (i = 0; i < cnt; i++) module_put(mods[i]); } static void free_user_syms(struct user_syms *us) { kvfree(us->syms); kvfree(us->buf); } static void bpf_kprobe_multi_link_release(struct bpf_link *link) { struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); unregister_fprobe(&kmulti_link->fp); kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt); } static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) { struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); kvfree(kmulti_link->addrs); kvfree(kmulti_link->cookies); kfree(kmulti_link->mods); kfree(kmulti_link); } static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { u64 __user *ucookies = u64_to_user_ptr(info->kprobe_multi.cookies); u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs); struct bpf_kprobe_multi_link *kmulti_link; u32 ucount = info->kprobe_multi.count; int err = 0, i; if (!uaddrs ^ !ucount) return -EINVAL; if (ucookies && !ucount) return -EINVAL; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); info->kprobe_multi.count = kmulti_link->cnt; info->kprobe_multi.flags = kmulti_link->flags; info->kprobe_multi.missed = kmulti_link->fp.nmissed; if (!uaddrs) return 0; if (ucount < kmulti_link->cnt) err = -ENOSPC; else ucount = kmulti_link->cnt; if (ucookies) { if (kmulti_link->cookies) { if (copy_to_user(ucookies, kmulti_link->cookies, ucount * sizeof(u64))) return -EFAULT; } else { for (i = 0; i < ucount; i++) { if (put_user(0, ucookies + i)) return -EFAULT; } } } if (kallsyms_show_value(current_cred())) { if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64))) return -EFAULT; } else { for (i = 0; i < ucount; i++) { if (put_user(0, uaddrs + i)) return -EFAULT; } } return err; } static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv) { const struct bpf_kprobe_multi_link *link = priv; unsigned long *addr_a = a, *addr_b = b; u64 *cookie_a, *cookie_b; cookie_a = link->cookies + (addr_a - link->addrs); cookie_b = link->cookies + (addr_b - link->addrs); /* swap addr_a/addr_b and cookie_a/cookie_b values */ swap(*addr_a, *addr_b); swap(*cookie_a, *cookie_b); } static int bpf_kprobe_multi_addrs_cmp(const void *a, const void *b) { const unsigned long *addr_a = a, *addr_b = b; if (*addr_a == *addr_b) return 0; return *addr_a < *addr_b ? -1 : 1; } static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv) { return bpf_kprobe_multi_addrs_cmp(a, b); } static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; struct bpf_kprobe_multi_link *link; u64 *cookie, entry_ip; unsigned long *addr; if (WARN_ON_ONCE(!ctx)) return 0; run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, session_ctx.run_ctx); link = run_ctx->link; if (!link->cookies) return 0; entry_ip = run_ctx->entry_ip; addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip), bpf_kprobe_multi_addrs_cmp); if (!addr) return 0; cookie = link->cookies + (addr - link->addrs); return *cookie; } static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, session_ctx.run_ctx); return run_ctx->entry_ip; } static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, unsigned long entry_ip, struct ftrace_regs *fregs, bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { .session_ctx = { .is_return = is_return, .data = data, }, .link = link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; struct pt_regs *regs; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { bpf_prog_inc_misses_counter(link->link.prog); err = 1; goto out; } migrate_disable(); rcu_read_lock(); regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr()); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); out: __this_cpu_dec(bpf_prog_active); return err; } static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } static void kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) { const char **str_a = (const char **) a; const char **str_b = (const char **) b; return strcmp(*str_a, *str_b); } struct multi_symbols_sort { const char **funcs; u64 *cookies; }; static void symbols_swap_r(void *a, void *b, int size, const void *priv) { const struct multi_symbols_sort *data = priv; const char **name_a = a, **name_b = b; swap(*name_a, *name_b); /* If defined, swap also related cookies. */ if (data->cookies) { u64 *cookie_a, *cookie_b; cookie_a = data->cookies + (name_a - data->funcs); cookie_b = data->cookies + (name_b - data->funcs); swap(*cookie_a, *cookie_b); } } struct modules_array { struct module **mods; int mods_cnt; int mods_cap; }; static int add_module(struct modules_array *arr, struct module *mod) { struct module **mods; if (arr->mods_cnt == arr->mods_cap) { arr->mods_cap = max(16, arr->mods_cap * 3 / 2); mods = krealloc_array(arr->mods, arr->mods_cap, sizeof(*mods), GFP_KERNEL); if (!mods) return -ENOMEM; arr->mods = mods; } arr->mods[arr->mods_cnt] = mod; arr->mods_cnt++; return 0; } static bool has_module(struct modules_array *arr, struct module *mod) { int i; for (i = arr->mods_cnt - 1; i >= 0; i--) { if (arr->mods[i] == mod) return true; } return false; } static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u32 addrs_cnt) { struct modules_array arr = {}; u32 i, err = 0; for (i = 0; i < addrs_cnt; i++) { bool skip_add = false; struct module *mod; scoped_guard(rcu) { mod = __module_address(addrs[i]); /* Either no module or it's already stored */ if (!mod || has_module(&arr, mod)) { skip_add = true; break; /* scoped_guard */ } if (!try_module_get(mod)) err = -EINVAL; } if (skip_add) continue; if (err) break; err = add_module(&arr, mod); if (err) { module_put(mod); break; } } /* We return either err < 0 in case of error, ... */ if (err) { kprobe_multi_put_modules(arr.mods, arr.mods_cnt); kfree(arr.mods); return err; } /* or number of modules found if everything is ok. */ *mods = arr.mods; return arr.mods_cnt; } static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt) { u32 i; for (i = 0; i < cnt; i++) { if (!within_error_injection_list(addrs[i])) return -EINVAL; } return 0; } int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_kprobe_multi_link *link = NULL; struct bpf_link_primer link_primer; void __user *ucookies; unsigned long *addrs; u32 flags, cnt, size; void __user *uaddrs; u64 *cookies = NULL; void __user *usyms; int err; /* no support for 32bit archs yet */ if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; if (attr->link_create.flags) return -EINVAL; if (!is_kprobe_multi(prog)) return -EINVAL; flags = attr->link_create.kprobe_multi.flags; if (flags & ~BPF_F_KPROBE_MULTI_RETURN) return -EINVAL; uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs); usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms); if (!!uaddrs == !!usyms) return -EINVAL; cnt = attr->link_create.kprobe_multi.cnt; if (!cnt) return -EINVAL; if (cnt > MAX_KPROBE_MULTI_CNT) return -E2BIG; size = cnt * sizeof(*addrs); addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); if (!addrs) return -ENOMEM; ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); if (ucookies) { cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); if (!cookies) { err = -ENOMEM; goto error; } if (copy_from_user(cookies, ucookies, size)) { err = -EFAULT; goto error; } } if (uaddrs) { if (copy_from_user(addrs, uaddrs, size)) { err = -EFAULT; goto error; } } else { struct multi_symbols_sort data = { .cookies = cookies, }; struct user_syms us; err = copy_user_syms(&us, usyms, cnt); if (err) goto error; if (cookies) data.funcs = us.syms; sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r, symbols_swap_r, &data); err = ftrace_lookup_symbols(us.syms, cnt, addrs); free_user_syms(&us); if (err) goto error; } if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) { err = -EINVAL; goto error; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; goto error; } bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI, &bpf_kprobe_multi_link_lops, prog); err = bpf_link_prime(&link->link, &link_primer); if (err) goto error; if (!(flags & BPF_F_KPROBE_MULTI_RETURN)) link->fp.entry_handler = kprobe_multi_link_handler; if ((flags & BPF_F_KPROBE_MULTI_RETURN) || is_kprobe_session(prog)) link->fp.exit_handler = kprobe_multi_link_exit_handler; if (is_kprobe_session(prog)) link->fp.entry_data_size = sizeof(u64); link->addrs = addrs; link->cookies = cookies; link->cnt = cnt; link->flags = flags; if (cookies) { /* * Sorting addresses will trigger sorting cookies as well * (check bpf_kprobe_multi_cookie_swap). This way we can * find cookie based on the address in bpf_get_attach_cookie * helper. */ sort_r(addrs, cnt, sizeof(*addrs), bpf_kprobe_multi_cookie_cmp, bpf_kprobe_multi_cookie_swap, link); } err = get_modules_for_addrs(&link->mods, addrs, cnt); if (err < 0) { bpf_link_cleanup(&link_primer); return err; } link->mods_cnt = err; err = register_fprobe_ips(&link->fp, addrs, cnt); if (err) { kprobe_multi_put_modules(link->mods, link->mods_cnt); bpf_link_cleanup(&link_primer); return err; } return bpf_link_settle(&link_primer); error: kfree(link); kvfree(addrs); kvfree(cookies); return err; } #else /* !CONFIG_FPROBE */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) { return 0; } static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { return 0; } #endif #ifdef CONFIG_UPROBES struct bpf_uprobe_multi_link; struct bpf_uprobe { struct bpf_uprobe_multi_link *link; loff_t offset; unsigned long ref_ctr_offset; u64 cookie; struct uprobe *uprobe; struct uprobe_consumer consumer; bool session; }; struct bpf_uprobe_multi_link { struct path path; struct bpf_link link; u32 cnt; u32 flags; struct bpf_uprobe *uprobes; struct task_struct *task; }; struct bpf_uprobe_multi_run_ctx { struct bpf_session_run_ctx session_ctx; unsigned long entry_ip; struct bpf_uprobe *uprobe; }; static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) { u32 i; for (i = 0; i < cnt; i++) uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer); if (cnt) uprobe_unregister_sync(); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) { struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt); if (umulti_link->task) put_task_struct(umulti_link->task); path_put(&umulti_link->path); } static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) { struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); kvfree(umulti_link->uprobes); kfree(umulti_link); } static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets); u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies); u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets); u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path); u32 upath_size = info->uprobe_multi.path_size; struct bpf_uprobe_multi_link *umulti_link; u32 ucount = info->uprobe_multi.count; int err = 0, i; char *p, *buf; long left = 0; if (!upath ^ !upath_size) return -EINVAL; if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount) return -EINVAL; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); info->uprobe_multi.count = umulti_link->cnt; info->uprobe_multi.flags = umulti_link->flags; info->uprobe_multi.pid = umulti_link->task ? task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0; upath_size = upath_size ? min_t(u32, upath_size, PATH_MAX) : PATH_MAX; buf = kmalloc(upath_size, GFP_KERNEL); if (!buf) return -ENOMEM; p = d_path(&umulti_link->path, buf, upath_size); if (IS_ERR(p)) { kfree(buf); return PTR_ERR(p); } upath_size = buf + upath_size - p; if (upath) left = copy_to_user(upath, p, upath_size); kfree(buf); if (left) return -EFAULT; info->uprobe_multi.path_size = upath_size; if (!uoffsets && !ucookies && !uref_ctr_offsets) return 0; if (ucount < umulti_link->cnt) err = -ENOSPC; else ucount = umulti_link->cnt; for (i = 0; i < ucount; i++) { if (uoffsets && put_user(umulti_link->uprobes[i].offset, uoffsets + i)) return -EFAULT; if (uref_ctr_offsets && put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) return -EFAULT; if (ucookies && put_user(umulti_link->uprobes[i].cookie, ucookies + i)) return -EFAULT; } return err; } static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, .dealloc_deferred = bpf_uprobe_multi_link_dealloc, .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; static int uprobe_prog_run(struct bpf_uprobe *uprobe, unsigned long entry_ip, struct pt_regs *regs, bool is_return, void *data) { struct bpf_uprobe_multi_link *link = uprobe->link; struct bpf_uprobe_multi_run_ctx run_ctx = { .session_ctx = { .is_return = is_return, .data = data, }, .entry_ip = entry_ip, .uprobe = uprobe, }; struct bpf_prog *prog = link->link.prog; bool sleepable = prog->sleepable; struct bpf_run_ctx *old_run_ctx; int err; if (link->task && !same_thread_group(current, link->task)) return 0; if (sleepable) rcu_read_lock_trace(); else rcu_read_lock(); migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); migrate_enable(); if (sleepable) rcu_read_unlock_trace(); else rcu_read_unlock(); return err; } static bool uprobe_multi_link_filter(struct uprobe_consumer *con, struct mm_struct *mm) { struct bpf_uprobe *uprobe; uprobe = container_of(con, struct bpf_uprobe, consumer); return uprobe->link->task->mm == mm; } static int uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs, __u64 *data) { struct bpf_uprobe *uprobe; int ret; uprobe = container_of(con, struct bpf_uprobe, consumer); ret = uprobe_prog_run(uprobe, instruction_pointer(regs), regs, false, data); if (uprobe->session) return ret ? UPROBE_HANDLER_IGNORE : 0; return 0; } static int uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs, __u64 *data) { struct bpf_uprobe *uprobe; uprobe = container_of(con, struct bpf_uprobe, consumer); uprobe_prog_run(uprobe, func, regs, true, data); return 0; } static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { struct bpf_uprobe_multi_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, session_ctx.run_ctx); return run_ctx->entry_ip; } static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx) { struct bpf_uprobe_multi_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, session_ctx.run_ctx); return run_ctx->uprobe->cookie; } int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_uprobe_multi_link *link = NULL; unsigned long __user *uref_ctr_offsets; struct bpf_link_primer link_primer; struct bpf_uprobe *uprobes = NULL; struct task_struct *task = NULL; unsigned long __user *uoffsets; u64 __user *ucookies; void __user *upath; u32 flags, cnt, i; struct path path; char *name; pid_t pid; int err; /* no support for 32bit archs yet */ if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; if (attr->link_create.flags) return -EINVAL; if (!is_uprobe_multi(prog)) return -EINVAL; flags = attr->link_create.uprobe_multi.flags; if (flags & ~BPF_F_UPROBE_MULTI_RETURN) return -EINVAL; /* * path, offsets and cnt are mandatory, * ref_ctr_offsets and cookies are optional */ upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; pid = attr->link_create.uprobe_multi.pid; if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets); ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies); name = strndup_user(upath, PATH_MAX); if (IS_ERR(name)) { err = PTR_ERR(name); return err; } err = kern_path(name, LOOKUP_FOLLOW, &path); kfree(name); if (err) return err; if (!d_is_reg(path.dentry)) { err = -EBADF; goto error_path_put; } if (pid) { rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); rcu_read_unlock(); if (!task) { err = -ESRCH; goto error_path_put; } } err = -ENOMEM; link = kzalloc(sizeof(*link), GFP_KERNEL); uprobes = kvcalloc(cnt, sizeof(*uprobes), GFP_KERNEL); if (!uprobes || !link) goto error_free; for (i = 0; i < cnt; i++) { if (__get_user(uprobes[i].offset, uoffsets + i)) { err = -EFAULT; goto error_free; } if (uprobes[i].offset < 0) { err = -EINVAL; goto error_free; } if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) { err = -EFAULT; goto error_free; } if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { err = -EFAULT; goto error_free; } uprobes[i].link = link; if (!(flags & BPF_F_UPROBE_MULTI_RETURN)) uprobes[i].consumer.handler = uprobe_multi_link_handler; if (flags & BPF_F_UPROBE_MULTI_RETURN || is_uprobe_session(prog)) uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler; if (is_uprobe_session(prog)) uprobes[i].session = true; if (pid) uprobes[i].consumer.filter = uprobe_multi_link_filter; } link->cnt = cnt; link->uprobes = uprobes; link->path = path; link->task = task; link->flags = flags; bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI, &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry), uprobes[i].offset, uprobes[i].ref_ctr_offset, &uprobes[i].consumer); if (IS_ERR(uprobes[i].uprobe)) { err = PTR_ERR(uprobes[i].uprobe); link->cnt = i; goto error_unregister; } } err = bpf_link_prime(&link->link, &link_primer); if (err) goto error_unregister; return bpf_link_settle(&link_primer); error_unregister: bpf_uprobe_unregister(uprobes, link->cnt); error_free: kvfree(uprobes); kfree(link); if (task) put_task_struct(task); error_path_put: path_put(&path); return err; } #else /* !CONFIG_UPROBES */ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx) { return 0; } static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { return 0; } #endif /* CONFIG_UPROBES */ __bpf_kfunc_start_defs(); __bpf_kfunc bool bpf_session_is_return(void) { struct bpf_session_run_ctx *session_ctx; session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); return session_ctx->is_return; } __bpf_kfunc __u64 *bpf_session_cookie(void) { struct bpf_session_run_ctx *session_ctx; session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); return session_ctx->data; } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(kprobe_multi_kfunc_set_ids) BTF_ID_FLAGS(func, bpf_session_is_return) BTF_ID_FLAGS(func, bpf_session_cookie) BTF_KFUNCS_END(kprobe_multi_kfunc_set_ids) static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id) { if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id)) return 0; if (!is_kprobe_session(prog) && !is_uprobe_session(prog)) return -EACCES; return 0; } static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { .owner = THIS_MODULE, .set = &kprobe_multi_kfunc_set_ids, .filter = bpf_kprobe_multi_filter, }; static int __init bpf_kprobe_multi_kfuncs_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); } late_initcall(bpf_kprobe_multi_kfuncs_init); typedef int (*copy_fn_t)(void *dst, const void *src, u32 size, struct task_struct *tsk); /* * The __always_inline is to make sure the compiler doesn't * generate indirect calls into callbacks, which is expensive, * on some kernel configurations. This allows compiler to put * direct calls into all the specific callback implementations * (copy_user_data_sleepable, copy_user_data_nofault, and so on) */ static __always_inline int __bpf_dynptr_copy_str(struct bpf_dynptr *dptr, u32 doff, u32 size, const void *unsafe_src, copy_fn_t str_copy_fn, struct task_struct *tsk) { struct bpf_dynptr_kern *dst; u32 chunk_sz, off; void *dst_slice; int cnt, err; char buf[256]; dst_slice = bpf_dynptr_slice_rdwr(dptr, doff, NULL, size); if (likely(dst_slice)) return str_copy_fn(dst_slice, unsafe_src, size, tsk); dst = (struct bpf_dynptr_kern *)dptr; if (bpf_dynptr_check_off_len(dst, doff, size)) return -E2BIG; for (off = 0; off < size; off += chunk_sz - 1) { chunk_sz = min_t(u32, sizeof(buf), size - off); /* Expect str_copy_fn to return count of copied bytes, including * zero terminator. Next iteration increment off by chunk_sz - 1 to * overwrite NUL. */ cnt = str_copy_fn(buf, unsafe_src + off, chunk_sz, tsk); if (cnt < 0) return cnt; err = __bpf_dynptr_write(dst, doff + off, buf, cnt, 0); if (err) return err; if (cnt < chunk_sz || chunk_sz == 1) /* we are done */ return off + cnt; } return off; } static __always_inline int __bpf_dynptr_copy(const struct bpf_dynptr *dptr, u32 doff, u32 size, const void *unsafe_src, copy_fn_t copy_fn, struct task_struct *tsk) { struct bpf_dynptr_kern *dst; void *dst_slice; char buf[256]; u32 off, chunk_sz; int err; dst_slice = bpf_dynptr_slice_rdwr(dptr, doff, NULL, size); if (likely(dst_slice)) return copy_fn(dst_slice, unsafe_src, size, tsk); dst = (struct bpf_dynptr_kern *)dptr; if (bpf_dynptr_check_off_len(dst, doff, size)) return -E2BIG; for (off = 0; off < size; off += chunk_sz) { chunk_sz = min_t(u32, sizeof(buf), size - off); err = copy_fn(buf, unsafe_src + off, chunk_sz, tsk); if (err) return err; err = __bpf_dynptr_write(dst, doff + off, buf, chunk_sz, 0); if (err) return err; } return 0; } static __always_inline int copy_user_data_nofault(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { return copy_from_user_nofault(dst, (const void __user *)unsafe_src, size); } static __always_inline int copy_user_data_sleepable(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { int ret; if (!tsk) { /* Read from the current task */ ret = copy_from_user(dst, (const void __user *)unsafe_src, size); if (ret) return -EFAULT; return 0; } ret = access_process_vm(tsk, (unsigned long)unsafe_src, dst, size, 0); if (ret != size) return -EFAULT; return 0; } static __always_inline int copy_kernel_data_nofault(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { return copy_from_kernel_nofault(dst, unsafe_src, size); } static __always_inline int copy_user_str_nofault(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { return strncpy_from_user_nofault(dst, (const void __user *)unsafe_src, size); } static __always_inline int copy_user_str_sleepable(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { int ret; if (unlikely(size == 0)) return 0; if (tsk) { ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_src, dst, size, 0); } else { ret = strncpy_from_user(dst, (const void __user *)unsafe_src, size - 1); /* strncpy_from_user does not guarantee NUL termination */ if (ret >= 0) ((char *)dst)[ret] = '\0'; } if (ret < 0) return ret; return ret + 1; } static __always_inline int copy_kernel_str_nofault(void *dst, const void *unsafe_src, u32 size, struct task_struct *tsk) { return strncpy_from_kernel_nofault(dst, unsafe_src, size); } __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type, u64 value) { if (type != PIDTYPE_PID && type != PIDTYPE_TGID) return -EINVAL; return bpf_send_signal_common(sig, type, task, value); } __bpf_kfunc int bpf_probe_read_user_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign) { return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_data_nofault, NULL); } __bpf_kfunc int bpf_probe_read_kernel_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void *unsafe_ptr__ign) { return __bpf_dynptr_copy(dptr, off, size, unsafe_ptr__ign, copy_kernel_data_nofault, NULL); } __bpf_kfunc int bpf_probe_read_user_str_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign) { return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_str_nofault, NULL); } __bpf_kfunc int bpf_probe_read_kernel_str_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void *unsafe_ptr__ign) { return __bpf_dynptr_copy_str(dptr, off, size, unsafe_ptr__ign, copy_kernel_str_nofault, NULL); } __bpf_kfunc int bpf_copy_from_user_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign) { return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_data_sleepable, NULL); } __bpf_kfunc int bpf_copy_from_user_str_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign) { return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_str_sleepable, NULL); } __bpf_kfunc int bpf_copy_from_user_task_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign, struct task_struct *tsk) { return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_data_sleepable, tsk); } __bpf_kfunc int bpf_copy_from_user_task_str_dynptr(struct bpf_dynptr *dptr, u32 off, u32 size, const void __user *unsafe_ptr__ign, struct task_struct *tsk) { return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign, copy_user_str_sleepable, tsk); } __bpf_kfunc_end_defs(); |
| 2 10 8 2 7 2 6 2 1 2 2 29 1 9 1 1 1 74 1 1 1 3 3 3 4 1 3 3 3 3 3 3 3 3 6 2 4 1 3 3 3 3 2 2 1 1 3 6 5 6 12 272 272 272 1 1 514 42 299 92 43 12 1 3 2 1 3 2 2 1 17 18 1 284 6 3 9 1 1189 1192 1187 1138 220 220 873 873 2 845 26 324 1 1 92 92 92 88 4 248 3 22 3 20 193 199 290 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kmod.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/net_tstamp.h> #include <linux/phylib_stubs.h> #include <linux/ptp_clock_kernel.h> #include <linux/wireless.h> #include <linux/if_bridge.h> #include <net/dsa_stubs.h> #include <net/netdev_lock.h> #include <net/wext.h> #include "dev.h" /* * Map an interface index to its name (SIOCGIFNAME) */ /* * We need this ioctl for efficient implementation of the * if_indextoname() function required by the IPv6 API. Without * it, we would have to search all the interfaces to find a * match. --pb */ static int dev_ifname(struct net *net, struct ifreq *ifr) { ifr->ifr_name[IFNAMSIZ-1] = 0; return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex); } /* * Perform a SIOCGIFCONF call. This structure will change * size eventually, and there is nothing I can do about it. * Thus we will need a 'compatibility mode'. */ int dev_ifconf(struct net *net, struct ifconf __user *uifc) { struct net_device *dev; void __user *pos; size_t size; int len, total = 0, done; /* both the ifconf and the ifreq structures are slightly different */ if (in_compat_syscall()) { struct compat_ifconf ifc32; if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf))) return -EFAULT; pos = compat_ptr(ifc32.ifcbuf); len = ifc32.ifc_len; size = sizeof(struct compat_ifreq); } else { struct ifconf ifc; if (copy_from_user(&ifc, uifc, sizeof(struct ifconf))) return -EFAULT; pos = ifc.ifc_buf; len = ifc.ifc_len; size = sizeof(struct ifreq); } /* Loop over the interfaces, and write an info block for each. */ rtnl_net_lock(net); for_each_netdev(net, dev) { if (!pos) done = inet_gifconf(dev, NULL, 0, size); else done = inet_gifconf(dev, pos + total, len - total, size); if (done < 0) { rtnl_net_unlock(net); return -EFAULT; } total += done; } rtnl_net_unlock(net); return put_user(total, &uifc->ifc_len); } static int dev_getifmap(struct net_device *dev, struct ifreq *ifr) { struct ifmap *ifmap = &ifr->ifr_map; if (in_compat_syscall()) { struct compat_ifmap *cifmap = (struct compat_ifmap *)ifmap; cifmap->mem_start = dev->mem_start; cifmap->mem_end = dev->mem_end; cifmap->base_addr = dev->base_addr; cifmap->irq = dev->irq; cifmap->dma = dev->dma; cifmap->port = dev->if_port; return 0; } ifmap->mem_start = dev->mem_start; ifmap->mem_end = dev->mem_end; ifmap->base_addr = dev->base_addr; ifmap->irq = dev->irq; ifmap->dma = dev->dma; ifmap->port = dev->if_port; return 0; } static int netif_setifmap(struct net_device *dev, struct ifreq *ifr) { struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map; if (!dev->netdev_ops->ndo_set_config) return -EOPNOTSUPP; if (in_compat_syscall()) { struct ifmap ifmap = { .mem_start = cifmap->mem_start, .mem_end = cifmap->mem_end, .base_addr = cifmap->base_addr, .irq = cifmap->irq, .dma = cifmap->dma, .port = cifmap->port, }; return dev->netdev_ops->ndo_set_config(dev, &ifmap); } return dev->netdev_ops->ndo_set_config(dev, &ifr->ifr_map); } /* * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) { int err; struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); if (!dev) return -ENODEV; switch (cmd) { case SIOCGIFFLAGS: /* Get interface flags */ ifr->ifr_flags = (short) dev_get_flags(dev); return 0; case SIOCGIFMETRIC: /* Get the metric on the interface (currently unused) */ ifr->ifr_metric = 0; return 0; case SIOCGIFMTU: /* Get the MTU of a device */ ifr->ifr_mtu = dev->mtu; return 0; case SIOCGIFSLAVE: err = -EINVAL; break; case SIOCGIFMAP: return dev_getifmap(dev, ifr); case SIOCGIFINDEX: ifr->ifr_ifindex = dev->ifindex; return 0; case SIOCGIFTXQLEN: ifr->ifr_qlen = dev->tx_queue_len; return 0; default: /* dev_ioctl() should ensure this case * is never reached */ WARN_ON(1); err = -ENOTTY; break; } return err; } int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg) { enum hwtstamp_tx_types tx_type; enum hwtstamp_rx_filters rx_filter; int tx_type_valid = 0; int rx_filter_valid = 0; if (cfg->flags & ~HWTSTAMP_FLAG_MASK) return -EINVAL; tx_type = cfg->tx_type; rx_filter = cfg->rx_filter; switch (tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: case HWTSTAMP_TX_ONESTEP_SYNC: case HWTSTAMP_TX_ONESTEP_P2P: tx_type_valid = 1; break; case __HWTSTAMP_TX_CNT: /* not a real value */ break; } switch (rx_filter) { case HWTSTAMP_FILTER_NONE: case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: rx_filter_valid = 1; break; case __HWTSTAMP_FILTER_CNT: /* not a real value */ break; } if (!tx_type_valid || !rx_filter_valid) return -ERANGE; return 0; } /** * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC * or of attached phylib PHY * @dev: Network device * @cfg: Timestamping configuration structure * * Helper for calling the default hardware provider timestamping. * * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and * there only exists a phydev->mii_ts->hwtstamp() method. So this will return * -EOPNOTSUPP for phylib for now, which is still more accurate than letting * the netdev handle the GET request. */ int dev_get_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct hwtstamp_provider *hwprov; hwprov = rtnl_dereference(dev->hwprov); if (hwprov) { cfg->qualifier = hwprov->desc.qualifier; if (hwprov->source == HWTSTAMP_SOURCE_PHYLIB && hwprov->phydev) return phy_hwtstamp_get(hwprov->phydev, cfg); if (hwprov->source == HWTSTAMP_SOURCE_NETDEV) return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); return -EOPNOTSUPP; } if (phy_is_default_hwtstamp(dev->phydev)) return phy_hwtstamp_get(dev->phydev, cfg); return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); } static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) { const struct net_device_ops *ops = dev->netdev_ops; struct kernel_hwtstamp_config kernel_cfg = {}; struct hwtstamp_config cfg; int err; if (!ops->ndo_hwtstamp_get) return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP); /* legacy */ if (!netif_device_present(dev)) return -ENODEV; kernel_cfg.ifr = ifr; netdev_lock_ops(dev); err = dev_get_hwtstamp_phylib(dev, &kernel_cfg); netdev_unlock_ops(dev); if (err) return err; /* If the request was resolved through an unconverted driver, omit * the copy_to_user(), since the implementation has already done that */ if (!kernel_cfg.copied_to_user) { hwtstamp_config_from_kernel(&cfg, &kernel_cfg); if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) return -EFAULT; } return 0; } /** * dev_set_hwtstamp_phylib() - Change hardware timestamping of NIC * or of attached phylib PHY * @dev: Network device * @cfg: Timestamping configuration structure * @extack: Netlink extended ack message structure, for error reporting * * Helper for enforcing a common policy that phylib timestamping, if available, * should take precedence in front of hardware timestamping provided by the * netdev. If the netdev driver needs to perform specific actions even for PHY * timestamping to work properly (a switch port must trap the timestamped * frames and not forward them), it must set dev->see_all_hwtstamp_requests. */ int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct kernel_hwtstamp_config old_cfg = {}; struct hwtstamp_provider *hwprov; struct phy_device *phydev; bool changed = false; bool phy_ts; int err; hwprov = rtnl_dereference(dev->hwprov); if (hwprov) { if (hwprov->source == HWTSTAMP_SOURCE_PHYLIB && hwprov->phydev) { phy_ts = true; phydev = hwprov->phydev; } else if (hwprov->source == HWTSTAMP_SOURCE_NETDEV) { phy_ts = false; } else { return -EOPNOTSUPP; } cfg->qualifier = hwprov->desc.qualifier; } else { phy_ts = phy_is_default_hwtstamp(dev->phydev); if (phy_ts) phydev = dev->phydev; } cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; if (phy_ts && dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_get(dev, &old_cfg); if (err) return err; } if (!phy_ts || dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_set(dev, cfg, extack); if (err) { if (extack->_msg) netdev_err(dev, "%s\n", extack->_msg); return err; } } if (phy_ts && dev->see_all_hwtstamp_requests) changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); if (phy_ts) { err = phy_hwtstamp_set(phydev, cfg, extack); if (err) { if (changed) ops->ndo_hwtstamp_set(dev, &old_cfg, NULL); return err; } } return 0; } static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { const struct net_device_ops *ops = dev->netdev_ops; struct kernel_hwtstamp_config kernel_cfg = {}; struct netlink_ext_ack extack = {}; struct hwtstamp_config cfg; int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; hwtstamp_config_to_kernel(&kernel_cfg, &cfg); kernel_cfg.ifr = ifr; err = net_hwtstamp_validate(&kernel_cfg); if (err) return err; err = dsa_conduit_hwtstamp_validate(dev, &kernel_cfg, &extack); if (err) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return err; } if (!ops->ndo_hwtstamp_set) return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP); /* legacy */ if (!netif_device_present(dev)) return -ENODEV; netdev_lock_ops(dev); err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack); netdev_unlock_ops(dev); if (err) return err; /* The driver may have modified the configuration, so copy the * updated version of it back to user space */ if (!kernel_cfg.copied_to_user) { hwtstamp_config_from_kernel(&cfg, &kernel_cfg); if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) return -EFAULT; } return 0; } static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, struct kernel_hwtstamp_config *kernel_cfg) { struct ifreq ifrr; int err; strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; err = dev_eth_ioctl(dev, &ifrr, cmd); if (err) return err; kernel_cfg->ifr->ifr_ifru = ifrr.ifr_ifru; kernel_cfg->copied_to_user = true; return 0; } int generic_hwtstamp_get_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg) { const struct net_device_ops *ops = dev->netdev_ops; if (!netif_device_present(dev)) return -ENODEV; if (ops->ndo_hwtstamp_get) return dev_get_hwtstamp_phylib(dev, kernel_cfg); /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); } EXPORT_SYMBOL(generic_hwtstamp_get_lower); int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; if (!netif_device_present(dev)) return -ENODEV; if (ops->ndo_hwtstamp_set) return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); } EXPORT_SYMBOL(generic_hwtstamp_set_lower); static int dev_siocbond(struct net_device *dev, struct ifreq *ifr, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocbond) { int ret = -ENODEV; netdev_lock_ops(dev); if (netif_device_present(dev)) ret = ops->ndo_siocbond(dev, ifr, cmd); netdev_unlock_ops(dev); return ret; } return -EOPNOTSUPP; } static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocdevprivate) { int ret = -ENODEV; netdev_lock_ops(dev); if (netif_device_present(dev)) ret = ops->ndo_siocdevprivate(dev, ifr, data, cmd); netdev_unlock_ops(dev); return ret; } return -EOPNOTSUPP; } static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocwandev) { int ret = -ENODEV; netdev_lock_ops(dev); if (netif_device_present(dev)) ret = ops->ndo_siocwandev(dev, ifs); netdev_unlock_ops(dev); return ret; } return -EOPNOTSUPP; } /* * Perform the SIOCxIFxxx calls, inside rtnl_net_lock() */ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, unsigned int cmd) { int err; struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); const struct net_device_ops *ops; if (!dev) return -ENODEV; ops = dev->netdev_ops; switch (cmd) { case SIOCSIFFLAGS: /* Set interface flags */ return dev_change_flags(dev, ifr->ifr_flags, NULL); case SIOCSIFMETRIC: /* Set the metric on the interface (currently unused) */ return -EOPNOTSUPP; case SIOCSIFMTU: /* Set the MTU of a device */ return dev_set_mtu(dev, ifr->ifr_mtu); case SIOCSIFHWADDR: if (dev->addr_len > sizeof(ifr->ifr_hwaddr)) return -EINVAL; return dev_set_mac_address_user(dev, (struct sockaddr_storage *)&ifr->ifr_hwaddr, NULL); case SIOCSIFHWBROADCAST: if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); netdev_lock_ops(dev); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); netdev_unlock_ops(dev); return 0; case SIOCSIFMAP: netdev_lock_ops(dev); err = netif_setifmap(dev, ifr); netdev_unlock_ops(dev); return err; case SIOCADDMULTI: if (!ops->ndo_set_rx_mode || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; netdev_lock_ops(dev); err = dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); netdev_unlock_ops(dev); return err; case SIOCDELMULTI: if (!ops->ndo_set_rx_mode || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; netdev_lock_ops(dev); err = dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); netdev_unlock_ops(dev); return err; case SIOCSIFTXQLEN: if (ifr->ifr_qlen < 0) return -EINVAL; return dev_change_tx_queue_len(dev, ifr->ifr_qlen); case SIOCSIFNAME: ifr->ifr_newname[IFNAMSIZ-1] = '\0'; return dev_change_name(dev, ifr->ifr_newname); case SIOCWANDEV: return dev_siocwandev(dev, &ifr->ifr_settings); case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15: return dev_siocdevprivate(dev, ifr, data, cmd); case SIOCSHWTSTAMP: return dev_set_hwtstamp(dev, ifr); case SIOCGHWTSTAMP: return dev_get_hwtstamp(dev, ifr); case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: return dev_eth_ioctl(dev, ifr, cmd); case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCBONDCHANGEACTIVE: return dev_siocbond(dev, ifr, cmd); /* Unknown ioctl */ default: err = -EINVAL; } return err; } /** * dev_load - load a network module * @net: the applicable net namespace * @name: name of interface * * If a network interface is not present and the process has suitable * privileges this function loads the module. If module loading is not * available in this kernel then it becomes a nop. */ void dev_load(struct net *net, const char *name) { struct net_device *dev; int no_module; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); rcu_read_unlock(); no_module = !dev; if (no_module && capable(CAP_NET_ADMIN)) no_module = request_module("netdev-%s", name); if (no_module && capable(CAP_SYS_MODULE)) request_module("%s", name); } EXPORT_SYMBOL(dev_load); /* * This function handles all "interface"-type I/O control requests. The actual * 'doing' part of this is dev_ifsioc above. */ /** * dev_ioctl - network device ioctl * @net: the applicable net namespace * @cmd: command to issue * @ifr: pointer to a struct ifreq in user space * @data: data exchanged with userspace * @need_copyout: whether or not copy_to_user() should be called * * Issue ioctl functions to devices. This is normally called by the * user space syscall interfaces but can sometimes be useful for * other purposes. The return value is the return from the syscall if * positive or a negative errno code on error. */ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout) { int ret; char *colon; if (need_copyout) *need_copyout = true; if (cmd == SIOCGIFNAME) return dev_ifname(net, ifr); ifr->ifr_name[IFNAMSIZ-1] = 0; colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; /* * See which interface the caller is talking about. */ switch (cmd) { case SIOCGIFHWADDR: dev_load(net, ifr->ifr_name); ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name); if (colon) *colon = ':'; return ret; /* * These ioctl calls: * - can be done by all. * - atomic and do not require locking. * - return a value */ case SIOCGIFFLAGS: case SIOCGIFMETRIC: case SIOCGIFMTU: case SIOCGIFSLAVE: case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: dev_load(net, ifr->ifr_name); rcu_read_lock(); ret = dev_ifsioc_locked(net, ifr, cmd); rcu_read_unlock(); if (colon) *colon = ':'; return ret; case SIOCETHTOOL: dev_load(net, ifr->ifr_name); ret = dev_ethtool(net, ifr, data); if (colon) *colon = ':'; return ret; /* * These ioctl calls: * - require superuser power. * - require strict serialization. * - return a value */ case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); rtnl_net_unlock(net); if (colon) *colon = ':'; return ret; /* * These ioctl calls: * - require superuser power. * - require strict serialization. * - do not return a value */ case SIOCSIFMAP: case SIOCSIFTXQLEN: if (!capable(CAP_NET_ADMIN)) return -EPERM; fallthrough; /* * These ioctl calls: * - require local superuser power. * - require strict serialization. * - do not return a value */ case SIOCSIFFLAGS: case SIOCSIFMETRIC: case SIOCSIFMTU: case SIOCSIFHWADDR: case SIOCSIFSLAVE: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCSIFHWBROADCAST: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCSHWTSTAMP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; fallthrough; case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); rtnl_net_unlock(net); if (need_copyout) *need_copyout = false; return ret; case SIOCGIFMEM: /* Get the per device memory space. We can add this but * currently do not support it */ case SIOCSIFMEM: /* Set the per device memory buffer space. * Not applicable in our case */ case SIOCSIFLINK: return -ENOTTY; /* * Unknown or private ioctl. */ default: if (cmd == SIOCWANDEV || cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr->ifr_name); rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); rtnl_net_unlock(net); return ret; } return -ENOTTY; } } |
| 120 3 117 12507 12514 12520 3 12506 12500 12332 172 172 12500 58 31 5 15 2 10 10 36 5 16 2 9 15 9 102 23 26 11 34 56 8 29 16 5 22 22 34 56 8 26 17 8 22 22 37 56 15 31 19 5 19 19 3 1 1 2 1 29 1 1 2 1 3 1 1 2 1 2 5 4 9 3 6 2 16 26 26 16 5 7 9 3 12 17 6 6 7 8 12 157 157 157 157 131 26 115 157 157 157 32 54 21 25 21 2 16 7 8 5 5 3 5 10 8 8 1 15 142 12 12 1 1 12 157 157 131 26 157 157 158 160 12 6 3 3 2 175 5 199 5 6 26 5 37 59 168 160 53 35 6 88 8 3 8 156 201 201 46 157 156 60 3 13 45 21 1 20 1 19 2 17 43 46 92 92 89 4 131 2 5 126 2 124 120 34 88 11 4 7 2 1 9 1 4 4 16 1 4 12 3 2 8 6 3 8 10 5 2 3 3 86 81 63 31 17 7 1 1 5 3 1 3 3 1 11 4 7 1 5 3 1 2 5 1 1 3 2 1 13 13 8 8 8 7 1 1 1 2 1 1 12 2 1 1 8 2 2 2 1 3 1 6 1 1 2 2 9 5 45 11 24 5 3 2 2 1 56 56 3 40 5 5 45 45 1 14 14 63 48 15 48 65 1 3 63 63 51 50 44 7 36 36 31 6 8 8 8 1 7 35 8 8 8 8 8 8 10 10 19 19 7 3 3 3 3 3 14 14 14 4 3 2 2 4 4 3 3 2 2 3 1 2 2 1 3 5 2 3 9 8 1 10 6 6 3 5 2 3 1 3 3 3 3 1 1 1 4 2 15 1 1 13 12 2 10 1 2 3 6 2 6 2 2 7 4 2 7 7 1 4 4 2 6 7 5 2 3 3 3 3 3 5 24 24 16 14 12 2 2 2 2 2 14 2 12 4 1 2 2 7 4 1 2 7 4 1 2 14 14 14 14 14 13 13 20 20 15 13 13 15 13 62 20 14 16 14 16 19 9 4 1 5 22 23 22 2 21 2 23 16 12 4 2 10 2 2 5 15 9 9 9 23 23 23 7 7 7 6 7 32 32 20 12 1 1 1 1 7 7 1 6 5 5 5 5 5 5 5 3 2 2 2 2 3 7 4 3 3 3 1 2 6 6 6 6 6 9 9 6 3 9 9 24 24 2 2 6 5 5 2 2 8 8 6 6 2 2 2 2 1 1 7 2 10 1 9 7 3 4 3 2 3 1 2 1 1 1 1 2 2 2 2 88 88 30 12 45 46 3 3 1 2 1888 130 1790 21 4 1 3 2 1 3 8 64 11 5 2 2 2 2 1 2 1 2 25 27 32 3 134 5 1 8 1 6 1 115 4 115 16 1 1 2 1 1 2 2 1 1 1 2 2 2 1 4 100 235 1 1 1 5 1 1 7 2 1 2 2 2 3 3 1 2 1 2 1 1 2 2 7 1 7 2 3 2 2 1 2 2 4 1 3 2 4 1 1 1 2 4 2 5 2 1 1 1 3 2 1 17 1 1 2 2 1 5 2 142 124 2 2 2 4 4 7 13 9 5 3 3 2 1 1 2 1 1 1 1 1 1 1 83 4 91 3 4 1 1 2 1 5 1 3 1 2 1 1 1 1 68 5 40 2 1 3 2 1 2 2 1 2 1 2 26 3 56 2 1 7 1 1 2 2 2 1 2 1 1 1 1 2 27 3 35 3 33 2 123 4 2 4 1 2 2 1 2 3 105 3 35 3 32 54 1 2 2 2 6 9 1 2 2 2 2 1 2 2 1 26 50 1 3 2 44 384 1 32 279 122 103 42 11 15 5 29 68 112 84 1 27 82 83 12 31 40 7 69 114 63 28 26 52 64 4 23 2 87 2 2 64 57 4 19 69 5 64 164 320 6 15 5 9 8 6 9 5 263 263 180 137 51 178 1 6 18 1 1 11 3 3 4 2 6 158 159 160 1 1 158 23 89 5 26 129 3 89 2 1 34 1 1 5 110 1 1 5 4 19 19 4 3 2 1 2 72 63 63 114 24 85 9 90 96 1 1 64 8 3 1 20 62 38 1 37 18 13 17 14 13 6 1 1 2 2 1 1 157 87 17 1 1 3 1 2 1 1 1 1 1 1 1 1 1 1 1 48 32 1 1 26 13 14 2 1 2 5 2 1 2 1 1 2 1 1 1 2 4 1 40 13 1 10 1 1 2 1 1 1 1 2 1 1 2 1 1 75 3 75 5 1 2 1 1 1 1 78 61 1 7 48 4 1 1 2 12 1 81 14 1 1 4 1 1 1 1 1 1 1 2 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 5 2 2 2 2 1 1 1 1 1 5 1 5 1 45 23 6 23 26 24 8 1 2 1 1 1 2 1 2 9 3 3 2 1 8 8 2 1 1 4 23 1 2 2 1 1 18 40 1 1 20 4 1 3 5 5 5 15 22 1 5 1 4 1 2 4 3 2 20 2 2 2 14 2 67 1 1 63 2 58 1 1 50 24 1 3 4 2 3 2 2 5 4 483 385 143 4 10 9 11 9 10 10 589 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/atomic.h> #include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/gfp.h> #include <net/inet_common.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/skmsg.h> #include <net/sock.h> #include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/udp.h> #include <linux/bpf_trace.h> #include <net/xdp_sock.h> #include <linux/inetdevice.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> #include <net/inet_dscp.h> #include "dev.h" /* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { struct compat_sock_fprog f32; if (len != sizeof(f32)) return -EINVAL; if (copy_from_sockptr(&f32, src, sizeof(f32))) return -EFAULT; memset(dst, 0, sizeof(*dst)); dst->len = f32.len; dst->filter = compat_ptr(f32.filter); } else { if (len != sizeof(*dst)) return -EINVAL; if (copy_from_sockptr(dst, src, sizeof(*dst))) return -EFAULT; } return 0; } EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); return -ENOMEM; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) return err; err = security_sock_rcv_skb(sk, skb); if (err) return err; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { struct sock *save_sk = skb->sk; unsigned int pkt_len; skb->sk = sk; pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(sk_filter_trim_cap); BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[a]; if (!nla_ok(nla, skb->len - a)) return 0; nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) { if (likely(offset >= 0)) return offset; if (offset >= SKF_NET_OFF) return offset - SKF_NET_OFF + skb_network_offset(skb); if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) return offset - SKF_LL_OFF + skb_mac_offset(skb); return INT_MIN; } BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { u8 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return *(u8 *)(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return tmp; else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be16 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be16(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be16_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be32 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be32(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be32_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, offset); } static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; switch (skb_field) { case SKF_AD_MARK: BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); break; case SKF_AD_PKTTYPE: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); #endif break; case SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, vlan_all)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } return insn - insn_buf; } static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); *insn++ = BPF_EXIT_INSN(); if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, ifindex)); else *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: cnt = convert_skb_access(SKF_AD_VLAN_TAG, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, vlan_proto)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = CTX */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); bpf_user_rnd_init_once(); break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: /* A ^= X */ *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: /* This is just a dummy call to avoid letting the compiler * evict __bpf_call_base() as an optimization. Placed here * where no-one bothers. */ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); return false; } *insnp = insn; return true; } static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) { const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); bool endian = BPF_SIZE(fp->code) == BPF_H || BPF_SIZE(fp->code) == BPF_W; bool indirect = BPF_MODE(fp->code) == BPF_IND; const int ip_align = NET_IP_ALIGN; struct bpf_insn *insn = *insnp; int offset = fp->k; if (!indirect && ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); if (offset) *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian + (!ldx_off_ok * 2)); if (ldx_off_ok) { *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_TMP, 0); } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); } *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); if (fp->k) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); } switch (BPF_SIZE(fp->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); break; default: return false; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn = BPF_EXIT_INSN(); *insnp = insn; return true; } /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_prog *new_prog, int *new_len, bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len > BPF_MAXINSNS) return -EINVAL; if (new_prog) { first_insn = new_prog->insnsi; addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } do_pass: new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); /* All programs must keep CTX in callee saved BPF_REG_CTX. * In eBPF case it's done by the compiler, here we need to * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); if (*seen_ld_abs) { /* For packet access in classic BPF, cache skb->data * in callee-saved BPF R8 and skb->len - skb->data_len * (headlen) in BPF R9. Since classic BPF is read-only * on CTX, we only need to cache it once. */ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), BPF_REG_D, BPF_REG_CTX, offsetof(struct sk_buff, data)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, offsetof(struct sk_buff, len)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, data_len)); *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: /* Check for overloaded BPF extension and * directly convert it if found, otherwise * just move on with mapping. */ if (BPF_CLASS(fp->code) == BPF_LD && BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; if (BPF_CLASS(fp->code) == BPF_LD && convert_bpf_ld_abs(fp, &insn)) { *seen_ld_abs = true; break; } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); /* Error with exception code on div/mod by 0. * For cBPF programs, this was always return 0. */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn++ = BPF_EXIT_INSN(); } *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; /* Jump transformation cannot use BPF block macros * everywhere as offset calculation and target updates * require a bit more work than the rest, i.e. jump * opcodes map as-is, but offsets need adjustment. */ #define BPF_EMIT_JMP \ do { \ const s32 off_min = S16_MIN, off_max = S16_MAX; \ s32 off; \ \ if (target >= len || target < 0) \ goto err; \ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ off -= insn - tmp_insns; \ /* Reject anything not fitting into insn->off. */ \ if (off < off_min || off > off_max) \ goto err; \ insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: target = i + fp->k + 1; insn->code = fp->code; BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { /* BPF immediates are signed, zero extend * immediate into tmp register and use it * in compare insn. */ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->dst_reg = BPF_REG_A; insn->src_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; BPF_EMIT_JMP; break; } /* Convert some jumps when 'jump_true' is next insn. */ if (fp->jt == 0) { switch (BPF_OP(fp->code)) { case BPF_JEQ: insn->code = BPF_JMP | BPF_JNE | bpf_src; break; case BPF_JGT: insn->code = BPF_JMP | BPF_JLE | bpf_src; break; case BPF_JGE: insn->code = BPF_JMP | BPF_JLT | bpf_src; break; default: goto jmp_rest; } target = i + fp->jf + 1; BPF_EMIT_JMP; break; } jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, .k = fp->k, }; *seen_ld_abs = true; /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ convert_bpf_ld_abs(&tmp, &insn); insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* tmp = X */ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } /* RET_K is remapped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: if (BPF_RVAL(fp->code) == BPF_K) *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, 0, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, -stack_off); /* check_load_and_stores() verifies that classic BPF can * load from stack only after write, so tracking * stack_depth for ST|STX insns is enough */ if (new_prog && new_prog->aux->stack_depth < stack_off) new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, -stack_off); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_CTX, offsetof(struct sk_buff, len)); break; /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; /* Unknown instruction. */ default: goto err; } insn++; if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); new_insn += insn - tmp_insns; } if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; if (*seen_ld_abs) *new_len += 4; /* Prologue bits. */ return 0; } pass++; if (new_flen != new_insn - first_insn) { new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; } kfree(addrs); BUG_ON(*new_len != new_flen); return 0; err: kfree(addrs); return -EINVAL; } /* Security: * * As we dont want to clear mem[] array for each packet going through * __bpf_prog_run(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { case BPF_ST: case BPF_STX: memvalid |= (1 << filter[pc].k); break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; case BPF_JMP | BPF_JA: /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; break; } } error: kfree(masks); return ret; } static bool chk_code_allowed(u16 code_to_probe) { static const bool codes[] = { /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_K] = true, [BPF_ALU | BPF_ADD | BPF_X] = true, [BPF_ALU | BPF_SUB | BPF_K] = true, [BPF_ALU | BPF_SUB | BPF_X] = true, [BPF_ALU | BPF_MUL | BPF_K] = true, [BPF_ALU | BPF_MUL | BPF_X] = true, [BPF_ALU | BPF_DIV | BPF_K] = true, [BPF_ALU | BPF_DIV | BPF_X] = true, [BPF_ALU | BPF_MOD | BPF_K] = true, [BPF_ALU | BPF_MOD | BPF_X] = true, [BPF_ALU | BPF_AND | BPF_K] = true, [BPF_ALU | BPF_AND | BPF_X] = true, [BPF_ALU | BPF_OR | BPF_K] = true, [BPF_ALU | BPF_OR | BPF_X] = true, [BPF_ALU | BPF_XOR | BPF_K] = true, [BPF_ALU | BPF_XOR | BPF_X] = true, [BPF_ALU | BPF_LSH | BPF_K] = true, [BPF_ALU | BPF_LSH | BPF_X] = true, [BPF_ALU | BPF_RSH | BPF_K] = true, [BPF_ALU | BPF_RSH | BPF_X] = true, [BPF_ALU | BPF_NEG] = true, /* Load instructions */ [BPF_LD | BPF_W | BPF_ABS] = true, [BPF_LD | BPF_H | BPF_ABS] = true, [BPF_LD | BPF_B | BPF_ABS] = true, [BPF_LD | BPF_W | BPF_LEN] = true, [BPF_LD | BPF_W | BPF_IND] = true, [BPF_LD | BPF_H | BPF_IND] = true, [BPF_LD | BPF_B | BPF_IND] = true, [BPF_LD | BPF_IMM] = true, [BPF_LD | BPF_MEM] = true, [BPF_LDX | BPF_W | BPF_LEN] = true, [BPF_LDX | BPF_B | BPF_MSH] = true, [BPF_LDX | BPF_IMM] = true, [BPF_LDX | BPF_MEM] = true, /* Store instructions */ [BPF_ST] = true, [BPF_STX] = true, /* Misc instructions */ [BPF_MISC | BPF_TAX] = true, [BPF_MISC | BPF_TXA] = true, /* Return instructions */ [BPF_RET | BPF_K] = true, [BPF_RET | BPF_A] = true, /* Jump instructions */ [BPF_JMP | BPF_JA] = true, [BPF_JMP | BPF_JEQ | BPF_K] = true, [BPF_JMP | BPF_JEQ | BPF_X] = true, [BPF_JMP | BPF_JGE | BPF_K] = true, [BPF_JMP | BPF_JGE | BPF_X] = true, [BPF_JMP | BPF_JGT | BPF_K] = true, [BPF_JMP | BPF_JGT | BPF_X] = true, [BPF_JMP | BPF_JSET | BPF_K] = true, [BPF_JMP | BPF_JSET | BPF_X] = true, }; if (code_to_probe >= ARRAY_SIZE(codes)) return false; return codes[code_to_probe]; } static bool bpf_check_basics_ok(const struct sock_filter *filter, unsigned int flen) { if (filter == NULL) return false; if (flen == 0 || flen > BPF_MAXINSNS) return false; return true; } /** * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * * Check the user's filter code. If we let some ugly * filter code slip through kaboom! The filter must contain * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * * All jumps are forward as they are not signed. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) return -EINVAL; /* Some instructions need special checks */ switch (ftest->code) { case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: if (ftest->k >= 32) return -EINVAL; break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; case BPF_JMP | BPF_JA: /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: anc_found = false; if (bpf_anc_helper(ftest) & BPF_ANC) anc_found = true; /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } } /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_RET | BPF_K: case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } return -EINVAL; } static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); if (!fp->orig_prog) return -ENOMEM; fkprog = fp->orig_prog; fkprog->len = fprog->len; fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; } return 0; } static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; if (fprog) { kfree(fprog->filter); kfree(fprog); } } static void __bpf_prog_release(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); bpf_prog_free(prog); } } static void __sk_filter_release(struct sk_filter *fp) { __bpf_prog_release(fp->prog); kfree(fp); } /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); __sk_filter_release(fp); } /** * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. */ static void sk_filter_release(struct sk_filter *fp) { if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); atomic_sub(filter_size, &sk->sk_omem_alloc); sk_filter_release(fp); } /* try to charge the socket memory if there is space available * return true on success */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); u32 filter_size = bpf_prog_size(fp->prog->len); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { if (!refcount_inc_not_zero(&fp->refcnt)) return false; if (!__sk_filter_charge(sk, fp)) { sk_filter_release(fp); return false; } return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it won't be used at * this point in time anymore internally after the migration to the eBPF * instruction representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; } /* 1st pass: calculate the new program length. */ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. */ fp = old_fp; err = -ENOMEM; goto out_err_free; } fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ err = bpf_convert_filter(old_prog, old_len, fp, &new_len, &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released * by krealloc(). */ goto out_err_free; fp = bpf_prog_select_runtime(fp, &err); if (err) goto out_err_free; kfree(old_prog); return fp; out_err_free: kfree(old_prog); out_err: __bpf_prog_release(fp); return ERR_PTR(err); } static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, bpf_aux_classic_check_t trans) { int err; fp->bpf_func = NULL; fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } /* There might be additional checks and transformations * needed on classic filters, f.e. in case of seccomp. */ if (trans) { err = trans(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } } /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ bpf_jit_compile(fp); /* JIT compiler couldn't process this filter, so do the eBPF translation * for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); return fp; } /** * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold * a copy here, and can spare us the work. */ fp->orig_prog = NULL; /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create); /** * bpf_prog_create_from_user - create an unattached filter from user buffer * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; int err; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { __bpf_prog_free(fp); return -EFAULT; } fp->len = fprog->len; fp->orig_prog = NULL; if (save_orig) { err = bpf_prog_store_orig_filter(fp, fprog); if (err) { __bpf_prog_free(fp); return -ENOMEM; } } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, trans); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); } EXPORT_SYMBOL_GPL(bpf_prog_destroy); static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) { struct sk_filter *fp, *old_fp; fp = kmalloc(sizeof(*fp), GFP_KERNEL); if (!fp) return -ENOMEM; fp->prog = prog; if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); return 0; } static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!prog) return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); return ERR_PTR(-EFAULT); } prog->len = fprog->len; err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ return bpf_prepare_filter(prog, NULL); } /** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use * * Attach the user's filter code. We first run some sanity checks on * it to make sure it does not explode on us later. If an error * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { __bpf_prog_release(prog); return err; } return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err, optmem_max; if (IS_ERR(prog)) return PTR_ERR(prog); optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); if (err) __bpf_prog_release(prog); return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) { if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); } int sk_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog = __get_bpf(ufd, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); return err; } return 0; } int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; int err, optmem_max; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { /* Like other non BPF_PROG_TYPE_SOCKET_FILTER * bpf prog (e.g. sockmap). It depends on the * limitation imposed by bpf_prog_load(). * Hence, sysctl_optmem_max is not checked. */ if ((sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) || (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_TCP) || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { err = -ENOTSUPP; goto err_prog_put; } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) { err = -ENOMEM; goto err_prog_put; } } err = reuseport_attach_prog(sk, prog); err_prog_put: if (err) bpf_prog_put(prog); return err; } void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) bpf_prog_put(prog); else bpf_prog_destroy(prog); } static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { #ifdef CONFIG_DEBUG_NET /* Avoid a splat in pskb_may_pull_reason() */ if (write_len > INT_MAX) return -EINVAL; #endif return skb_ensure_writable(skb, write_len); } static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_pointers(skb); return err; } static int bpf_try_make_head_writable(struct sk_buff *skb) { return bpf_try_make_writable(skb, skb_headlen(skb)); } static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); } static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len, u64, flags) { void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return ____bpf_skb_store_bytes(skb, offset, from, len, flags); } BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return ____bpf_skb_load_bytes(skb, offset, to, len); } BPF_CALL_4(bpf_flow_dissector_load_bytes, const struct bpf_flow_dissector *, ctx, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > 0xffff)) goto err_clear; if (unlikely(!ctx->skb)) goto err_clear; ptr = skb_header_pointer(ctx->skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { .func = bpf_flow_dissector_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); u8 *start, *ptr; if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: if (unlikely(!skb_mac_header_was_set(skb))) goto err_clear; start = skb_mac_header(skb); break; case BPF_HDR_START_NET: start = skb_network_header(skb); break; default: goto err_clear; } ptr = start + offset; if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { .func = bpf_skb_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto bpf_skb_pull_data_proto = { .func = bpf_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } static const struct bpf_func_proto bpf_sk_fullsock_proto = { .func = bpf_sk_fullsock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto sk_skb_pull_data_proto = { .func = sk_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; csum_replace_by_diff(ptr, to); break; case 2: csum_replace2(ptr, from, to); break; case 4: csum_replace4(ptr, from, to); break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; case 4: inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); break; default: return -EINVAL; } if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; return 0; } static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data * from_size > 0, to_size == 0, seed := csum --> pulling data * from_size > 0, to_size > 0, seed := 0 --> diffing data * * Even for diffing, from_size and to_size don't need to be equal. */ __wsum ret = seed; if (from_size && to_size) ret = csum_sub(csum_partial(to, to_size, ret), csum_partial(from, from_size, 0)); else if (to_size) ret = csum_partial(to, to_size, ret); else if (from_size) ret = ~csum_partial(from, from_size, ~ret); return csum_from32to16((__force unsigned int)ret); } static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) { /* The interface is to be used in combination with bpf_csum_diff() * for direct packet writes. csum rotation for alignment as well * as emulating csum_sub() can be done from the eBPF program. */ if (skb->ip_summed == CHECKSUM_COMPLETE) return (skb->csum = csum_add(skb->csum, csum)); return -ENOTSUPP; } static const struct bpf_func_proto bpf_csum_update_proto = { .func = bpf_csum_update, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) { /* The interface is to be used in combination with bpf_skb_adjust_room() * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET * is passed as flags, for example. */ switch (level) { case BPF_CSUM_LEVEL_INC: __skb_incr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_DEC: __skb_decr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_RESET: __skb_reset_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_QUERY: return skb->ip_summed == CHECKSUM_UNNECESSARY ? skb->csum_level : -EACCES; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_csum_level_proto = { .func = bpf_csum_level, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb_nomtu(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; ret = netif_rx(skb); } return ret; } static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; } skb->dev = dev; skb_set_redirected_noclear(skb, skb_at_tc_ingress(skb)); skb_clear_tstamp(skb); dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); dev_xmit_recursion_dec(); return ret; } static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { unsigned int mlen = skb_network_offset(skb); if (unlikely(skb->len <= mlen)) { kfree_skb(skb); return -ERANGE; } if (mlen) { __skb_pull(skb, mlen); /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that * the skb is originated from ingress (i.e. a forwarded skb) * to ensure that rcsum starts at net header. */ if (!skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, u32 flags) { if (dev_is_mac_header_xmit(dev)) return __bpf_redirect_common(skb, dev, flags); else return __bpf_redirect_no_mac(skb, dev, flags); } #if IS_ENABLED(CONFIG_IPV6) static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *nexthop; struct dst_entry *dst = NULL; struct neighbour *neigh; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; } neigh = ip_neigh_gw6(dev, nexthop); if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); if (dst) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowi6_mark = skb->mark, .flowlabel = ip6_flowinfo(ip6h), .flowi6_oif = dev->ifindex, .flowi6_proto = ip6h->nexthdr, .daddr = ip6h->daddr, .saddr = ip6h->saddr, }; dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) goto out_drop; skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; } err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_IPV6 */ #if IS_ENABLED(CONFIG_INET) static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { struct rtable *rt = skb_rtable(skb); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { rcu_read_unlock(); goto out_drop; } if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct iphdr *ip4h = ip_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)), .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; struct rtable *rt; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out_drop; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out_drop; } skb_dst_set(skb, &rt->dst); } err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_INET */ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { struct ethhdr *ethh = eth_hdr(skb); if (unlikely(skb->mac_header >= skb->network_header)) goto out; bpf_push_mac_rcsum(skb); if (is_multicast_ether_addr(ethh->h_dest)) goto out; skb_pull(skb, sizeof(*ethh)); skb_unset_mac_header(skb); skb_reset_network_header(skb); if (skb->protocol == htons(ETH_P_IP)) return __bpf_redirect_neigh_v4(skb, dev, nh); else if (skb->protocol == htons(ETH_P_IPV6)) return __bpf_redirect_neigh_v6(skb, dev, nh); out: kfree_skb(skb); return -ENOTSUPP; } /* Internal, non-exposed redirect flags. */ enum { BPF_F_NEIGH = (1ULL << 16), BPF_F_PEER = (1ULL << 17), BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; clone = skb_clone(skb, GFP_ATOMIC); if (unlikely(!clone)) return -ENOMEM; /* For direct write, we need to keep the invariant that the skbs * we're dealing with need to be uncloned. Should uncloning fail * here, we need to free the just generated clone to unclone once * again. */ ret = bpf_try_make_head_writable(skb); if (unlikely(ret)) { kfree_skb(clone); return -ENOMEM; } return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; if (likely(ops->ndo_get_peer_dev)) return INDIRECT_CALL_1(ops->ndo_get_peer_dev, netkit_peer_dev, dev); return NULL; } int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; ri->flags = 0; if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? &ri->nh : NULL) : __bpf_redirect(skb, dev, flags); out_drop: kfree_skb(skb); return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_peer_proto = { .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); if (plen) memcpy(&ri->nh, params, sizeof(ri->nh)); return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_neigh_proto = { .func = bpf_redirect_neigh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; } static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .func = bpf_msg_apply_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; } static void sk_msg_reset_curr(struct sk_msg *msg) { if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else { u32 i = msg->sg.end; sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, u32, end, u64, flags) { u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; u32 first_sge, last_sge, i, shift, bytes_sg_total; struct scatterlist *sge; u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to * copy into a linear buffer exclusively owned by BPF. Then * place the buffer in the scatterlist and fixup the original * entries by removing the entries now in the linear buffer * and shifting the remaining entries. For now we do not try * to copy partial entries to avoid complexity of running out * of sg_entry slots. The downside is reading a single byte * will copy the entire sg entry. */ do { copy += sk_msg_elem(msg, i)->length; sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; } while (i != msg->sg.end); last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy)); if (unlikely(!page)) return -ENOMEM; raw = page_address(page); i = first_sge; do { sge = sk_msg_elem(msg, i); from = sg_virt(sge); len = sge->length; to = raw + poffset; memcpy(to, from, len); poffset += len; sge->length = 0; put_page(sg_page(sge)); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; i = first_sge; sk_msg_iter_var_next(i); do { u32 move_from; if (i + shift >= NR_MSG_FRAG_IDS) move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) break; msg->sg.data[i] = msg->sg.data[move_from]; msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; sk_msg_iter_var_next(i); } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; } static const struct bpf_func_proto bpf_msg_pull_data_proto = { .func = bpf_msg_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (start > offset + l) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); /* If no space available will fallback to copy, we need at * least one scatterlist elem available to push data into * when start aligns to the beginning of an element or two * when it falls inside an element. We handle the start equals * offset case because its the common case for inserting a * header. */ if (!space || (space == 1 && start != offset)) copy = msg->sg.data[i].length; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy + len)); if (unlikely(!page)) return -ENOMEM; if (copy) { int front, back; raw = page_address(page); if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); front = start - offset; back = psge->length - front; from = sg_virt(psge); if (front) memcpy(raw, from, front); if (back) { from += front; to = raw + front + len; memcpy(to, from, back); } put_page(sg_page(psge)); new = i; goto place_new; } if (start - offset) { if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); psge->length = start - offset; rsge.length -= psge->length; rsge.offset += start; sk_msg_iter_var_next(i); sg_unmark_end(psge); sg_unmark_end(&rsge); } /* Slot(s) to place newly allocated data */ sk_msg_iter_next(msg, end); new = i; sk_msg_iter_var_next(i); if (i == msg->sg.end) { if (!rsge.length) goto place_new; sk_msg_iter_next(msg, end); goto place_new; } /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; sge = nsge; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; nnsge = sk_msg_elem_cpy(msg, i); } else { nsge = sk_msg_elem_cpy(msg, i); } } place_new: /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; } sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_push_data_proto = { .func = bpf_msg_push_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static void sk_msg_shift_left(struct sk_msg *msg, int i) { struct scatterlist *sge = sk_msg_elem(msg, i); int prev; put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); while (i != msg->sg.end) { msg->sg.data[i] = sge; sk_msg_iter_var_next(i); sge = tmp; tmp = sk_msg_elem_cpy(msg, i); } } BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); pop = len; /* --------------| offset * -| start |-------- len -------| * * |----- a ----|-------- pop -------|----- b ----| * |______________________________________________| length * * * a: region at front of scatter element to save * b: region at back of scatter element to save when length > A + pop * pop: region to pop from element, same as input 'pop' here will be * decremented below per iteration. * * Two top-level cases to handle when start != offset, first B is non * zero and second B is zero corresponding to when a pop includes more * than one element. * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to * the right free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); nsge = sk_msg_elem(msg, i); get_page(sg_page(sge)); sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); } else { struct page *page, *orig; u8 *to, *from; page = alloc_pages(__GFP_NOWARN | __GFP_COMP | GFP_ATOMIC, get_order(a + b)); if (unlikely(!page)) return -ENOMEM; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); put_page(orig); } pop = 0; } else { pop -= (sge->length - a); sge->length = a; } } /* From above the current layout _must_ be as follows, * * -| offset * -| start * * |---- pop ---|---------------- b ------------| * |____________________________________________| length * * Offset and start of the current msg elem are equal because in the * previous case we handled offset != start and either consumed the * entire element and advanced to the next element OR pop == 0. * * Two cases to handle here are first pop is less than the length * leaving some remainder b above. Simply adjust the element's layout * in this case. Or pop >= length of the element so that b = 0. In this * case advance to next element decrementing pop. */ while (pop) { struct scatterlist *sge = sk_msg_elem(msg, i); if (pop < sge->length) { sge->length -= pop; sge->offset += pop; pop = 0; } else { pop -= sge->length; sk_msg_shift_left(msg, i); } } sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_pop_data_proto = { .func = bpf_msg_pop_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_NET_CLASSID BPF_CALL_0(bpf_get_cgroup_classid_curr) { return __task_get_classid(current); } const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return 0; return sock_cgroup_classid(&sk->sk_cgrp_data); } static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { .func = bpf_skb_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .func = bpf_get_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { .func = bpf_get_route_realm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .func = bpf_get_hash_recalc, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) { /* After all direct packet write, this can be used once for * triggering a lazy recalc on next skb_get_hash() invocation. */ skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .func = bpf_set_hash_invalid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) { /* Set user specified hash as L4(+), so that it gets returned * on skb_get_hash() call unless BPF prog later on triggers a * skb_clear_hash(). */ __skb_set_sw_hash(skb, hash, true); return 0; } static const struct bpf_func_proto bpf_set_hash_proto = { .func = bpf_set_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { int ret; bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) { skb->protocol = htons(proto); if (skb_valid_dst(skb)) skb_dst_drop(skb); } static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, * so no need to do it here. */ skb_push(skb, len); memmove(skb->data, skb->data + len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) * needed here as it does not change the skb->csum * result for checksum complete when summing over * zeroed blocks. */ return 0; } static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { void *old_data; /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); memmove(skb->data, old_data, off); return 0; } static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* There's no need for __skb_push()/__skb_pull() pair to * get to the start of the mac header as we're guaranteed * to always start from here under eBPF. */ ret = bpf_skb_generic_push(skb, off, len); if (likely(!ret)) { skb->mac_header -= len; skb->network_header -= len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* Same here, __skb_push()/__skb_pull() pair not needed. */ ret = bpf_skb_generic_pop(skb, off, len); if (likely(!ret)) { skb->mac_header += len; skb->network_header += len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } } bpf_skb_change_protocol(skb, ETH_P_IPV6); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } } bpf_skb_change_protocol(skb, ETH_P_IP); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { __be16 from_proto = skb->protocol; if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) return bpf_skb_proto_4_to_6(skb); if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) return bpf_skb_proto_6_to_4(skb); return -ENOTSUPP; } BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, u64, flags) { int ret; if (unlikely(flags)) return -EINVAL; /* General idea is that this helper does the basic groundwork * needed for changing the protocol, and eBPF program fills the * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace() * and other helpers, rather than passing a raw buffer here. * * The rationale is to keep this minimal and without a need to * deal with raw packet data. F.e. even if we would pass buffers * here, the program still needs to call the bpf_lX_csum_replace() * helpers anyway. Plus, this way we keep also separation of * concerns, since f.e. bpf_skb_store_bytes() should only take * care of stores. * * Currently, additional options and extension header space are * not supported, but flags register is reserved so we can adapt * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_proto_proto = { .func = bpf_skb_change_proto, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; return 0; } static const struct bpf_func_proto bpf_skb_change_type_proto = { .func = bpf_skb_change_type, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): return sizeof(struct ipv6hdr); default: return ~0U; } } #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) #define BPF_F_ADJ_ROOM_DECAP_L3_MASK (BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_DECAP_L3_IPV6) #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK) | \ BPF_F_ADJ_ROOM_DECAP_L3_MASK) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; unsigned int gso_type = SKB_GSO_DODGY; int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_cow_head(skb, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -ENOTSUPP; if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE && flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH && inner_mac_len < ETH_HLEN) return -EINVAL; if (skb->encapsulation) return -EALREADY; mac_len = skb->network_header - skb->mac_header; inner_net = skb->network_header; if (inner_mac_len > len_diff) return -EINVAL; inner_trans = skb->transport_header; } ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH) skb_set_inner_protocol(skb, htons(ETH_P_TEB)); else skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) gso_type |= SKB_GSO_UDP_TUNNEL; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE) gso_type |= SKB_GSO_GRE; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) gso_type |= SKB_GSO_IPXIP6; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) gso_type |= SKB_GSO_IPXIP4; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE || flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) { int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); skb_set_transport_header(skb, mac_len + nh_len); } /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; /* Due to header growth, MSS needs to be downgraded. * There is a BUG_ON() when segmenting the frag_list with * head_frag true, so linearize the skb after downgrading * the MSS. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { skb_decrease_gso_size(shinfo, len_diff); if (shinfo->frag_list) return skb_linearize(skb); } } return 0; } static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_DECAP_L3_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Due to header shrink, MSS can be upgraded. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } return 0; } #define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_diff_abs = abs(len_diff); bool shrink = len_diff < 0; int ret = 0; if (unlikely(flags || mode)) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (!shrink) { ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; __skb_push(skb, len_diff_abs); memset(skb->data, 0, len_diff_abs); } else { if (unlikely(!pskb_may_pull(skb, len_diff_abs))) return -ENOMEM; __skb_pull(skb, len_diff_abs); } if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); rxm->full_len += len_diff; } return ret; } static const struct bpf_func_proto sk_skb_adjust_room_proto = { .func = sk_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (unlikely(proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))) return -ENOTSUPP; off = skb_mac_header_len(skb); switch (mode) { case BPF_ADJ_ROOM_NET: off += bpf_skb_net_base_len(skb); break; case BPF_ADJ_ROOM_MAC: break; default: return -ENOTSUPP; } if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { if (!shrink) return -EINVAL; switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: len_min = sizeof(struct iphdr); break; case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: len_min = sizeof(struct ipv6hdr); break; default: return -EINVAL; } } len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || (!shrink && (skb->len + len_diff_abs > len_max && !skb_is_gso(skb)))) return -ENOTSUPP; ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_adjust_room_proto = { .func = bpf_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static u32 __bpf_skb_min_len(const struct sk_buff *skb) { int offset = skb_network_offset(skb); u32 min_len = 0; if (offset > 0) min_len = offset; if (skb_transport_header_was_set(skb)) { offset = skb_transport_offset(skb); if (offset > 0) min_len = offset; } if (skb->ip_summed == CHECKSUM_PARTIAL) { offset = skb_checksum_start_offset(skb) + skb->csum_offset + sizeof(__sum16); if (offset > 0) min_len = offset; } return min_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; int ret; ret = __skb_grow_rcsum(skb, new_len); if (!ret) memset(skb->data + old_len, 0, new_len - old_len); return ret; } static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) { return __skb_trim_rcsum(skb, new_len); } static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) return -EINVAL; if (skb->encapsulation) return -ENOTSUPP; /* The basic idea of this helper is that it's performing the * needed work to either grow or trim an skb, and eBPF program * rewrites the rest via helpers like bpf_skb_store_bytes(), * bpf_lX_csum_replace() and others rather than passing a raw * buffer here. This one is a slow path helper and intended * for replies with control messages. * * Like in bpf_skb_change_proto(), we want to keep this rather * minimal and without protocol specifics so that we are able * to separate concerns as in bpf_skb_store_bytes() should only * be the one responsible for writing buffers. * * It's really expected to be a slow path operation here for * control message replies, so we're implicitly linearizing, * uncloning and drop offloads from the skb by this. */ ret = __bpf_try_make_writable(skb, skb->len); if (!ret) { if (new_len > skb->len) ret = bpf_skb_grow_rcsum(skb, new_len); else if (new_len < skb->len) ret = bpf_skb_trim_rcsum(skb, new_len); if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } return ret; } BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_tail_proto = { .func = bpf_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { .func = sk_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; ret = skb_cow(skb, head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that * skb->protocol network header, etc, stay as is. * Compared to bpf_skb_change_tail(), we're more * flexible due to not needing to linearize or * reset GSO. Intention for this helper is to be * used by an L3 skb that needs to push mac header * for redirection into L2 device. */ __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); } return ret; } BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { .func = bpf_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { .func = sk_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) { return xdp_get_buff_len(xdp); } static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], }; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; } BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; if (metalen) memmove(xdp->data_meta + offset, xdp->data_meta, metalen); xdp->data_meta += offset; xdp->data = data; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .func = bpf_xdp_adjust_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { unsigned long ptr_len, ptr_off = 0; skb_frag_t *next_frag, *end_frag; struct skb_shared_info *sinfo; void *src, *dst; u8 *ptr_buf; if (likely(xdp->data_end - xdp->data >= off + len)) { src = flush ? buf : xdp->data + off; dst = flush ? xdp->data + off : buf; memcpy(dst, src, len); return; } sinfo = xdp_get_shared_info_from_buff(xdp); end_frag = &sinfo->frags[sinfo->nr_frags]; next_frag = &sinfo->frags[0]; ptr_len = xdp->data_end - xdp->data; ptr_buf = xdp->data; while (true) { if (off < ptr_off + ptr_len) { unsigned long copy_off = off - ptr_off; unsigned long copy_len = min(len, ptr_len - copy_off); src = flush ? buf : ptr_buf + copy_off; dst = flush ? ptr_buf + copy_off : buf; memcpy(dst, src, copy_len); off += copy_len; len -= copy_len; buf += copy_len; } if (!len || next_frag == end_frag) break; ptr_off += ptr_len; ptr_buf = skb_frag_address(next_frag); ptr_len = skb_frag_size(next_frag); next_frag++; } } void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { u32 size = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; void *addr = xdp->data; int i; if (unlikely(offset > 0xffff || len > 0xffff)) return ERR_PTR(-EFAULT); if (unlikely(offset + len > xdp_get_buff_len(xdp))) return ERR_PTR(-EINVAL); if (likely(offset < size)) /* linear area */ goto out; sinfo = xdp_get_shared_info_from_buff(xdp); offset -= size; for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ u32 frag_size = skb_frag_size(&sinfo->frags[i]); if (offset < frag_size) { addr = skb_frag_address(&sinfo->frags[i]); size = frag_size; break; } offset -= frag_size; } out: return offset + len <= size ? addr + offset : NULL; } BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, false); else memcpy(buf, ptr, len); return 0; } static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { .func = bpf_xdp_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_load_bytes(xdp, offset, buf, len); } BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, true); else memcpy(ptr, buf, len); return 0; } static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { .func = bpf_xdp_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_store_bytes(xdp, offset, buf, len); } static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; unsigned int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); if (unlikely(offset > tailroom)) return -EINVAL; memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); skb_frag_size_add(frag, offset); sinfo->xdp_frags_size += offset; if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) xsk_buff_get_tail(xdp)->data_end += offset; return 0; } static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, enum xdp_mem_type mem_type, bool release) { struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp); if (release) { xsk_buff_del_tail(zc_frag); __xdp_return(0, mem_type, false, zc_frag); } else { zc_frag->data_end -= shrink; } } static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, int shrink) { enum xdp_mem_type mem_type = xdp->rxq->mem.type; bool release = skb_frag_size(frag) == shrink; if (mem_type == MEM_TYPE_XSK_BUFF_POOL) { bpf_xdp_shrink_data_zc(xdp, shrink, mem_type, release); goto out; } if (release) __xdp_return(skb_frag_netmem(frag), mem_type, false, NULL); out: return release; } static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, n_frags_free = 0, len_free = 0; if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) return -EINVAL; for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { skb_frag_t *frag = &sinfo->frags[i]; int shrink = min_t(int, offset, skb_frag_size(frag)); len_free += shrink; offset -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink)) { n_frags_free++; } else { skb_frag_size_sub(frag, shrink); break; } } sinfo->nr_frags -= n_frags_free; sinfo->xdp_frags_size -= len_free; if (unlikely(!sinfo->nr_frags)) { xdp_buff_clear_frags_flag(xdp); xdp->data_end -= offset; } return 0; } BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ if (offset < 0) return bpf_xdp_frags_shrink_tail(xdp, -offset); return bpf_xdp_frags_increase_tail(xdp, offset); } /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; /* Clear memory area on grow, can contain uninit kernel memory */ if (offset > 0) memset(xdp->data_end, 0, offset); xdp->data_end = data_end; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { .func = bpf_xdp_adjust_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely(xdp_metalen_invalid(metalen))) return -EACCES; xdp->data_meta = meta; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .func = bpf_xdp_adjust_meta, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; /** * DOC: xdp redirect * * XDP_REDIRECT works by a three-step process, implemented in the functions * below: * * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target * of the redirect and store it (along with some other metadata) in a per-CPU * struct bpf_redirect_info. * * 2. When the program returns the XDP_REDIRECT return code, the driver will * call xdp_do_redirect() which will use the information in struct * bpf_redirect_info to actually enqueue the frame into a map type-specific * bulk queue structure. * * 3. Before exiting its NAPI poll loop, the driver will call * xdp_do_flush(), which will flush all the different bulk queues, * thus completing the redirect. Note that xdp_do_flush() must be * called before napi_complete_done() in the driver, as the * XDP_REDIRECT logic relies on being inside a single NAPI instance * through to the xdp_do_flush() call for RCU protection of all * in-kernel data structures. */ /* * Pointers to the map entries will be kept around for this whole sequence of * steps, protected by RCU. However, there is no top-level rcu_read_lock() in * the core code; instead, the RCU protection relies on everything happening * inside a single NAPI poll sequence, which means it's between a pair of calls * to local_bh_disable()/local_bh_enable(). * * The map entries are marked as __rcu and the map code makes sure to * dereference those pointers with rcu_dereference_check() in a way that works * for both sections that to hold an rcu_read_lock() and sections that are * called from NAPI without a separate rcu_read_lock(). The code below does not * use RCU annotations, but relies on those in the map code. */ void xdp_do_flush(void) { struct list_head *lh_map, *lh_dev, *lh_xsk; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) __dev_flush(lh_dev); if (lh_map) __cpu_map_flush(lh_map); if (lh_xsk) __xsk_map_flush(lh_xsk); } EXPORT_SYMBOL_GPL(xdp_do_flush); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) void xdp_do_check_flushed(struct napi_struct *napi) { struct list_head *lh_map, *lh_dev, *lh_xsk; bool missed = false; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) { __dev_flush(lh_dev); missed = true; } if (lh_map) { __cpu_map_flush(lh_map); missed = true; } if (lh_xsk) { __xsk_map_flush(lh_xsk); missed = true; } WARN_ONCE(missed, "Missing xdp_do_flush() invocation after NAPI by %ps\n", napi->poll); } #endif DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); if (slave && slave != xdp->rxq->dev) { /* The target device is different from the receiving device, so * redirect it to the new device. * Using XDP_REDIRECT gets the correct behaviour from XDP enabled * drivers to unmap the packet from their rx ring. */ ri->tgt_index = slave->ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } return XDP_TX; } EXPORT_SYMBOL_GPL(xdp_master_redirect); static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, const struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; err = __xsk_map_redirect(fwd, xdp); if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, struct net_device *dev, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { err = -EOVERFLOW; goto err; } switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; break; } err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; default: err = -EBADRQC; } if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog, void *fwd, enum bpf_map_type map_type, u32 map_id, u32 flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } if (unlikely(err)) goto err; break; case BPF_MAP_TYPE_XSKMAP: err = xsk_generic_rcv(fwd, xdp); if (err) goto err; consume_skb(skb); break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_generic_redirect(fwd, skb); if (unlikely(err)) goto err; break; default: err = -EBADRQC; goto err; } _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = xdp_ok_fwd_dev(fwd, skb->len); if (unlikely(err)) goto err; skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index); generic_xdp_tx(skb, xdp_prog); return 0; } return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; } BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; /* NB! Map type UNSPEC and map_id == INT_MAX (never generated * by map_idr) is used for ifindex based XDP redirect. */ ri->tgt_index = ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_proto = { .func = bpf_xdp_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; if (ptr != dst_buff) memcpy(dst_buff, ptr, len); return 0; } BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, bpf_skb_copy); } static const struct bpf_func_proto bpf_skb_event_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, u32, size, u64, flags) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; int err; if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS)))) { err = -EINVAL; goto err_clear; } if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) { err = -EPROTO; goto err_clear; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) goto err_clear; set_compat: to = (struct bpf_tunnel_key *)compat; break; default: goto err_clear; } } to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); memcpy(to->local_ipv6, &info->key.u.ipv6.dst, sizeof(to->local_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst); memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy(to_orig, to, size); return 0; err_clear: memset(to_orig, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; if (unlikely(!info || !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } if (unlikely(size < info->options_len)) { err = -ENOMEM; goto err_clear; } ip_tunnel_info_opts_get(to, info); if (size > info->options_len) memset(to + info->options_len, 0, size - info->options_len); return info->options_len; err_clear: memset(to, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .func = bpf_skb_get_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, const struct bpf_tunnel_key *, from, u32, size, u64, flags) { struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER | BPF_F_NO_TUNNEL_KEY))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; } } if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, flags & BPF_F_DONT_FRAGMENT); __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, !(flags & BPF_F_ZERO_CSUM_TX)); __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, flags & BPF_F_SEQ_NUMBER); __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; if (flags & BPF_F_TUNINFO_IPV6) { info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); memcpy(&info->key.u.ipv6.src, from->local_ipv6, sizeof(from->local_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4); info->key.flow_flags = FLOWI_FLAG_ANYSRC; } return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, const u8 *, from, u32, size) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_set_options_present(present); ip_tunnel_info_opts_set(info, from, size, present); return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .func = bpf_skb_set_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { struct metadata_dst __percpu *tmp; tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tmp) return NULL; if (cmpxchg(&md_dst, NULL, tmp)) metadata_dst_free_percpu(tmp); } switch (which) { case BPF_FUNC_skb_set_tunnel_key: return &bpf_skb_set_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_opt: return &bpf_skb_set_tunnel_opt_proto; default: return NULL; } } BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return sk_under_cgroup_hierarchy(sk, cgrp); } static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SOCK_CGROUP_DATA static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .func = bpf_skb_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, int ancestor_level) { struct cgroup *ancestor; struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) return 0; return cgroup_id(ancestor); } BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) { return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); } static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { struct xdp_buff *xdp = (struct xdp_buff *)ctx; bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } static const struct bpf_func_proto bpf_xdp_event_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .func = bpf_get_socket_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .func = bpf_get_socket_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .func = bpf_get_socket_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) { return sk ? sock_gen_cookie(sk) : 0; } const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { .func = bpf_get_socket_ptr_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | PTR_MAYBE_NULL, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .func = bpf_get_socket_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static u64 __bpf_get_netns_cookie(struct sock *sk) { const struct net *net = sk ? sock_net(sk) : &init_net; return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie, struct sk_buff *, skb) { return __bpf_get_netns_cookie(skb && skb->sk ? skb->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_proto = { .func = bpf_get_netns_cookie, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) { return __bpf_get_netns_cookie(ctx); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { .func = bpf_get_netns_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .func = bpf_get_netns_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = { .func = bpf_get_netns_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = { .func = bpf_get_netns_cookie_sk_msg, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); kuid_t kuid; if (!sk || !sk_fullsock(sk)) return overflowuid; kuid = sock_net_uid(sock_net(sk), sk); return from_kuid_munged(sock_net(sk)->user_ns, kuid); } static const struct bpf_func_proto bpf_get_socket_uid_proto = { .func = bpf_get_socket_uid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt) { u32 sk_bpf_cb_flags; if (getopt) { *(u32 *)optval = sk->sk_bpf_cb_flags; return 0; } sk_bpf_cb_flags = *(u32 *)optval; if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK) return -EINVAL; sk->sk_bpf_cb_flags = sk_bpf_cb_flags; return 0; } static int sol_socket_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { switch (optname) { case SO_REUSEADDR: case SO_SNDBUF: case SO_RCVBUF: case SO_KEEPALIVE: case SO_PRIORITY: case SO_REUSEPORT: case SO_RCVLOWAT: case SO_MARK: case SO_MAX_PACING_RATE: case SO_BINDTOIFINDEX: case SO_TXREHASH: case SK_BPF_CB_FLAGS: if (*optlen != sizeof(int)) return -EINVAL; break; case SO_BINDTODEVICE: break; default: return -EINVAL; } if (optname == SK_BPF_CB_FLAGS) return sk_bpf_set_get_cb_flags(sk, optval, getopt); if (getopt) { if (optname == SO_BINDTODEVICE) return -EINVAL; return sk_getsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return sk_setsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), *optlen); } static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname, char *optval, int optlen) { if (optlen != sizeof(int)) return -EINVAL; switch (optname) { case TCP_BPF_SOCK_OPS_CB_FLAGS: { int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags; memcpy(optval, &cb_flags, optlen); break; } case TCP_BPF_RTO_MIN: { int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min); memcpy(optval, &rto_min_us, optlen); break; } case TCP_BPF_DELACK_MAX: { int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max); memcpy(optval, &delack_max_us, optlen); break; } default: return -EINVAL; } return 0; } static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, char *optval, int optlen) { struct tcp_sock *tp = tcp_sk(sk); unsigned long timeout; int val; if (optlen != sizeof(int)) return -EINVAL; val = *(int *)optval; /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: if (val <= 0 || tp->data_segs_out > tp->syn_data) return -EINVAL; tcp_snd_cwnd_set(tp, val); break; case TCP_BPF_SNDCWND_CLAMP: if (val <= 0) return -EINVAL; tp->snd_cwnd_clamp = val; tp->snd_ssthresh = val; break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); if (timeout > TCP_DELACK_MAX || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; case TCP_BPF_RTO_MIN: timeout = usecs_to_jiffies(val); if (timeout > TCP_RTO_MIN || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; case TCP_BPF_SOCK_OPS_CB_FLAGS: if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) return -EINVAL; tp->bpf_sock_ops_cb_flags = val; break; default: return -EINVAL; } return 0; } static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, int *optlen, bool getopt) { struct tcp_sock *tp; int ret; if (*optlen < 2) return -EINVAL; if (getopt) { if (!inet_csk(sk)->icsk_ca_ops) return -EINVAL; /* BPF expects NULL-terminated tcp-cc string */ optval[--(*optlen)] = '\0'; return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } /* "cdg" is the only cc that alloc a ptr * in inet_csk_ca area. The bpf-tcp-cc may * overwrite this ptr after switching to cdg. */ if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) return -ENOTSUPP; /* It stops this looping * * .init => bpf_setsockopt(tcp_cc) => .init => * bpf_setsockopt(tcp_cc)" => .init => .... * * The second bpf_setsockopt(tcp_cc) is not allowed * in order to break the loop when both .init * are the same bpf prog. * * This applies even the second bpf_setsockopt(tcp_cc) * does not cause a loop. This limits only the first * '.init' can call bpf_setsockopt(TCP_CONGESTION) to * pick a fallback cc (eg. peer does not support ECN) * and the second '.init' cannot fallback to * another. */ tp = tcp_sk(sk); if (tp->bpf_chg_cc_inprogress) return -EBUSY; tp->bpf_chg_cc_inprogress = 1; ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), *optlen); tp->bpf_chg_cc_inprogress = 0; return ret; } static int sol_tcp_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_protocol != IPPROTO_TCP) return -EINVAL; switch (optname) { case TCP_NODELAY: case TCP_MAXSEG: case TCP_KEEPIDLE: case TCP_KEEPINTVL: case TCP_KEEPCNT: case TCP_SYNCNT: case TCP_WINDOW_CLAMP: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_USER_TIMEOUT: case TCP_NOTSENT_LOWAT: case TCP_SAVE_SYN: case TCP_RTO_MAX_MS: if (*optlen != sizeof(int)) return -EINVAL; break; case TCP_CONGESTION: return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt); case TCP_SAVED_SYN: if (*optlen < 1) return -EINVAL; break; default: if (getopt) return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen); return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); } if (getopt) { if (optname == TCP_SAVED_SYN) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->saved_syn || *optlen > tcp_saved_syn_len(tp->saved_syn)) return -EINVAL; memcpy(optval, tp->saved_syn->data, *optlen); /* It cannot free tp->saved_syn here because it * does not know if the user space still needs it. */ return 0; } return do_tcp_getsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return do_tcp_setsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ip_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET) return -EINVAL; switch (optname) { case IP_TOS: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return do_ip_getsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return do_ip_setsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ipv6_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET6) return -EINVAL; switch (optname) { case IPV6_TCLASS: case IPV6_AUTOFLOWLABEL: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), *optlen); } static int __bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (!sk_fullsock(sk)) return -EINVAL; if (level == SOL_SOCKET) return sol_socket_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) return sol_ip_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) return sol_ipv6_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) return sol_tcp_sockopt(sk, optname, optval, &optlen, false); return -EINVAL; } static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock) { return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB; } static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_setsockopt(sk, level, optname, optval, optlen); } static int __bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { int err, saved_optlen = optlen; if (!sk_fullsock(sk)) { err = -EINVAL; goto done; } if (level == SOL_SOCKET) err = sol_socket_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) err = sol_tcp_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) err = sol_ip_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true); else err = -EINVAL; done: if (err) optlen = 0; if (optlen < saved_optlen) memset(optval + optlen, 0, saved_optlen - optlen); return err; } static int _bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_getsockopt(sk, level, optname, optval, optlen); } BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_setsockopt_proto = { .func = bpf_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_getsockopt_proto = { .func = bpf_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto = { .func = bpf_unlocked_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto = { .func = bpf_unlocked_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .func = bpf_sock_addr_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .func = bpf_sock_addr_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .func = bpf_sock_ops_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, int optname, const u8 **start) { struct sk_buff *syn_skb = bpf_sock->syn_skb; const u8 *hdr_start; int ret; if (syn_skb) { /* sk is a request_sock here */ if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } else { /* optname == TCP_BPF_SYN_MAC */ hdr_start = skb_mac_header(syn_skb); ret = skb_mac_header_len(syn_skb) + skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; struct saved_syn *saved_syn; if (sk->sk_state == TCP_NEW_SYN_RECV) /* synack retransmit. bpf_sock->syn_skb will * not be available. It has to resort to * saved_syn (if it is saved). */ saved_syn = inet_reqsk(sk)->saved_syn; else saved_syn = tcp_sk(sk)->saved_syn; if (!saved_syn) return -ENOENT; if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; } else if (optname == TCP_BPF_SYN_IP) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen; ret = saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } else { /* optname == TCP_BPF_SYN_MAC */ /* TCP_SAVE_SYN may not have saved the mac hdr */ if (!saved_syn->mac_hdrlen) return -ENOENT; hdr_start = saved_syn->data; ret = saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } *start = hdr_start; return ret; } BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); if (ret > 0) { copy_len = ret; if (optlen < copy_len) { copy_len = optlen; ret = -ENOSPC; } memcpy(optval, start, copy_len); } /* Zero out unused buffer at the end */ memset(optval + copy_len, 0, optlen - copy_len); return ret; } return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, int, argval) { struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { .func = bpf_sock_ops_cb_flags_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; EXPORT_SYMBOL_GPL(ipv6_bpf_stub); BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, int, addr_len) { #ifdef CONFIG_INET struct sock *sk = ctx->sk; u32 flags = BIND_FROM_BPF; int err; err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet_bind(sk, addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_bind_proto = { .func = bpf_bind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #ifdef CONFIG_XFRM #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) struct metadata_dst __percpu *xfrm_bpf_md_dst; EXPORT_SYMBOL_GPL(xfrm_bpf_md_dst); #endif BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { const struct sec_path *sp = skb_sec_path(skb); const struct xfrm_state *x; if (!sp || unlikely(index >= sp->len || flags)) goto err_clear; x = sp->xvec[index]; if (unlikely(size != sizeof(struct bpf_xfrm_state))) goto err_clear; to->reqid = x->props.reqid; to->spi = x->id.spi; to->family = x->props.family; to->ext = 0; if (to->family == AF_INET6) { memcpy(to->remote_ipv6, x->props.saddr.a6, sizeof(to->remote_ipv6)); } else { to->remote_ipv4 = x->props.saddr.a4; memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); } return 0; err_clear: memset(to, 0, size); return -EINVAL; } static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { .func = bpf_skb_get_xfrm_state, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) params->mtu_result = mtu; /* union with tot_len */ return 0; } #endif #if IS_ENABLED(CONFIG_INET) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct fib_nh_common *nhc; struct in_device *in_dev; struct neighbour *neigh; struct net_device *dev; struct fib_result res; struct flowi4 fl4; u32 mtu = 0; int err; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; fl4.flowi4_oif = params->ifindex; } else { fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } fl4.flowi4_tos = params->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.flowi4_proto = params->l4_protocol; fl4.daddr = params->ipv4_dst; fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl4.flowi4_mark = params->mark; else fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } if (err) { /* map fib lookup errors to RTN_ type */ if (err == -EINVAL) return BPF_FIB_LKUP_RET_BLACKHOLE; if (err == -EHOSTUNREACH) return BPF_FIB_LKUP_RET_UNREACHABLE; if (err == -EACCES) return BPF_FIB_LKUP_RET_PROHIBIT; return BPF_FIB_LKUP_RET_NOT_FWDED; } if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } nhc = res.nhc; /* do not handle lwt encaps right now */ if (nhc->nhc_lwtstate) return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) params->ipv4_src = fib_result_prefsrc(net, &res); /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; if (likely(nhc->nhc_gw_family != AF_INET6)) neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); else neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #if IS_ENABLED(CONFIG_IPV6) static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; struct flowi6 fl6; int strict = 0; int oif, err; u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; oif = fl6.flowi6_oif = params->ifindex; } else { oif = fl6.flowi6_iif = params->ifindex; fl6.flowi6_oif = 0; strict = RT6_LOOKUP_F_HAS_SADDR; } fl6.flowlabel = params->flowinfo; fl6.flowi6_scope = 0; fl6.flowi6_flags = 0; fl6.mp_hash = 0; fl6.flowi6_proto = params->l4_protocol; fl6.daddr = *dst; fl6.saddr = *src; fl6.fl6_sport = params->sport; fl6.fl6_dport = params->dport; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl6.flowi6_mark = params->mark; else fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict); } if (unlikely(err || IS_ERR_OR_NULL(res.f6i) || res.f6i == net->ipv6.fib6_null_entry)) return BPF_FIB_LKUP_RET_NOT_FWDED; switch (res.fib6_type) { /* only unicast is forwarded */ case RTN_UNICAST: break; case RTN_BLACKHOLE: return BPF_FIB_LKUP_RET_BLACKHOLE; case RTN_UNREACHABLE: return BPF_FIB_LKUP_RET_UNREACHABLE; case RTN_PROHIBIT: return BPF_FIB_LKUP_RET_PROHIBIT; default: return BPF_FIB_LKUP_RET_NOT_FWDED; } ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif, fl6.flowi6_oif != 0, NULL, strict); if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } if (res.nh->fib_nh_lws) return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (res.nh->fib_nh_gw_family) *dst = res.nh->fib_nh_gw6; dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) { if (res.f6i->fib6_prefsrc.plen) { *src = res.f6i->fib6_prefsrc.addr; } else { err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, &fl6.daddr, 0, src); if (err) return BPF_FIB_LKUP_RET_NO_SRC_ADDR; } } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif } return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .func = bpf_xdp_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) check_mtu = true; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; /* When tot_len isn't provided by user, check skb * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .func = bpf_skb_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, u32 ifindex) { struct net *netns = dev_net(dev_curr); /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ if (ifindex == 0) return dev_curr; return dev_get_by_index_rcu(netns, ifindex); } BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int mtu, dev_len, skb_len; if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) return -EINVAL; if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len; skb_len += len_diff; /* minus result pass check */ if (skb_len <= dev_len) { ret = BPF_MTU_CHK_RET_SUCCESS; goto out; } /* At this point, skb->len exceed MTU, but as it include length of all * segments, it can still be below MTU. The SKB can possibly get * re-segmented in transmit path (see validate_xmit_skb). Thus, user * must choose if segs are to be MTU checked. */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; if (flags & BPF_MTU_CHK_SEGS && !skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } out: *mtu_len = mtu; return ret; } BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ if (unlikely(flags)) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ if (*mtu_len) xdp_len = *mtu_len + dev->hard_header_len; xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; *mtu_len = mtu; return ret; } static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .func = bpf_skb_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .func = bpf_xdp_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { int err; struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; if (!seg6_validate_srh(srh, len, false)) return -EINVAL; switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); break; case BPF_LWT_ENCAP_SEG6: skb_reset_inner_headers(skb); skb->encapsulation = 1; err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); break; default: return -EINVAL; } bpf_compute_data_pointers(skb); if (err) return err; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); } #endif /* CONFIG_IPV6_SEG6_BPF */ #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) { return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); } #endif BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_LWT_ENCAP_SEG6: case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); #endif default: return -EINVAL; } } BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, false /* egress */); #endif default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .func = bpf_lwt_in_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .func = bpf_lwt_seg6_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { srh_state->srh = NULL; } else { srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen = srh_state->srh->hdrlen << 3; srh_state->valid = true; } } BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int hdroff = 0; int err; lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_DT6: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) return -EBADMSG; if (!pskb_pull(skb, hdroff)) return -EBADMSG; skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; bpf_compute_data_pointers(skb); bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) bpf_update_srh_state(skb); return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) bpf_update_srh_state(skb); return err; default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .func = bpf_lwt_seg6_action, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; struct ipv6hdr *hdr; int srhoff = 0; int ret; lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (unlikely(ptr < srh_tlvs || ptr > srh_end)) return -EFAULT; if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) return -EFAULT; if (len > 0) { ret = skb_cow_head(skb, len); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, offset, len); } else { ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); } bpf_compute_data_pointers(skb); if (unlikely(ret < 0)) return ret; hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; srh_state->valid = false; return 0; } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .func = bpf_lwt_seg6_adjust_srh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_IPV6_SEG6_BPF */ #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; bool refcounted = false; struct sock *sk = NULL; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) sk = __inet_lookup(net, hinfo, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, net->ipv4.udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, hinfo, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, net->ipv4.udp_table, NULL); #endif } if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); sk = NULL; } return sk; } /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = NULL; struct net *net; u8 family; if (len == sizeof(tuple->ipv4)) family = AF_INET; else if (len == sizeof(tuple->ipv6)) family = AF_INET6; else return NULL; if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (sdif < 0) { if (family == AF_INET) sdif = inet_sdif(skb); else sdif = inet6_sdif(skb); } if ((s32)netns_id < 0) { net = caller_net; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } out: return sk; } static struct sock * __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, sdif); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } static struct sock * bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct net *caller_net; int ifindex; if (skb->dev) { caller_net = dev_net(skb->dev); ifindex = skb->dev->ifindex; } else { caller_net = sock_net(skb->sk); ifindex = 0; } return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, -1); } static struct sock * bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .func = bpf_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .func = bpf_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .func = bpf_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = { .func = bpf_tc_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = { .func = bpf_tc_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = { .func = bpf_tc_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_release, struct sock *, sk) { if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .func = bpf_xdp_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .func = bpf_xdp_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .func = bpf_xdp_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .func = bpf_sock_addr_skc_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .func = bpf_sock_addr_sk_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_UDP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .func = bpf_sock_addr_sk_lookup_udp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, icsk_retransmits)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_tcp_sock, bytes_received): case offsetof(struct bpf_tcp_sock, bytes_acked): return size == sizeof(__u64); default: return size == sizeof(__u32); } } u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ } while (0) #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ si->dst_reg, si->src_reg, \ offsetof( \ struct inet_connection_sock, \ FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_tcp_sock); switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; case offsetof(struct bpf_tcp_sock, snd_cwnd): BPF_TCP_SOCK_GET_COMMON(snd_cwnd); break; case offsetof(struct bpf_tcp_sock, srtt_us): BPF_TCP_SOCK_GET_COMMON(srtt_us); break; case offsetof(struct bpf_tcp_sock, snd_ssthresh): BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); break; case offsetof(struct bpf_tcp_sock, rcv_nxt): BPF_TCP_SOCK_GET_COMMON(rcv_nxt); break; case offsetof(struct bpf_tcp_sock, snd_nxt): BPF_TCP_SOCK_GET_COMMON(snd_nxt); break; case offsetof(struct bpf_tcp_sock, snd_una): BPF_TCP_SOCK_GET_COMMON(snd_una); break; case offsetof(struct bpf_tcp_sock, mss_cache): BPF_TCP_SOCK_GET_COMMON(mss_cache); break; case offsetof(struct bpf_tcp_sock, ecn_flags): BPF_TCP_SOCK_GET_COMMON(ecn_flags); break; case offsetof(struct bpf_tcp_sock, rate_delivered): BPF_TCP_SOCK_GET_COMMON(rate_delivered); break; case offsetof(struct bpf_tcp_sock, rate_interval_us): BPF_TCP_SOCK_GET_COMMON(rate_interval_us); break; case offsetof(struct bpf_tcp_sock, packets_out): BPF_TCP_SOCK_GET_COMMON(packets_out); break; case offsetof(struct bpf_tcp_sock, retrans_out): BPF_TCP_SOCK_GET_COMMON(retrans_out); break; case offsetof(struct bpf_tcp_sock, total_retrans): BPF_TCP_SOCK_GET_COMMON(total_retrans); break; case offsetof(struct bpf_tcp_sock, segs_in): BPF_TCP_SOCK_GET_COMMON(segs_in); break; case offsetof(struct bpf_tcp_sock, data_segs_in): BPF_TCP_SOCK_GET_COMMON(data_segs_in); break; case offsetof(struct bpf_tcp_sock, segs_out): BPF_TCP_SOCK_GET_COMMON(segs_out); break; case offsetof(struct bpf_tcp_sock, data_segs_out): BPF_TCP_SOCK_GET_COMMON(data_segs_out); break; case offsetof(struct bpf_tcp_sock, lost_out): BPF_TCP_SOCK_GET_COMMON(lost_out); break; case offsetof(struct bpf_tcp_sock, sacked_out): BPF_TCP_SOCK_GET_COMMON(sacked_out); break; case offsetof(struct bpf_tcp_sock, bytes_received): BPF_TCP_SOCK_GET_COMMON(bytes_received); break; case offsetof(struct bpf_tcp_sock, bytes_acked): BPF_TCP_SOCK_GET_COMMON(bytes_acked); break; case offsetof(struct bpf_tcp_sock, dsack_dups): BPF_TCP_SOCK_GET_COMMON(dsack_dups); break; case offsetof(struct bpf_tcp_sock, delivered): BPF_TCP_SOCK_GET_COMMON(delivered); break; case offsetof(struct bpf_tcp_sock, delivered_ce): BPF_TCP_SOCK_GET_COMMON(delivered_ce); break; case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; } return insn - insn_buf; } BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) { sk = sk_to_full_sk(sk); if (sk && sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) return (unsigned long)sk; return (unsigned long)NULL; } static const struct bpf_func_proto bpf_get_listener_sock_proto = { .func = bpf_get_listener_sock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); break; case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); break; default: return 0; } if (skb_headlen(skb) < iphdr_len) return 0; if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) return 0; return INET_ECN_set_ce(skb); } bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) return false; if (off % size != 0) return false; switch (off) { default: return size == sizeof(__u32); } } u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_XDP_SOCK_GET(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ } while (0) switch (si->off) { case offsetof(struct bpf_xdp_sock, queue_id): BPF_XDP_SOCK_GET(queue_id); break; } return insn - insn_buf; } static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES int ret; if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (ret > 0) return 0; return -ENOENT; #else return -ENOTSUPP; #endif } static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .func = bpf_tcp_check_syncookie, .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; u16 mss; if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) return -EINVAL; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); #else return -EOPNOTSUPP; #endif /* CONFIG_SYN_COOKIES */ } static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .func = bpf_tcp_gen_syncookie, .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_pfree; return 0; } static const struct bpf_func_proto bpf_sk_assign_proto = { .func = bpf_sk_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, u8 search_kind, const u8 *magic, u8 magic_len, bool *eol) { u8 kind, kind_len; *eol = false; while (op < opend) { kind = op[0]; if (kind == TCPOPT_EOL) { *eol = true; return ERR_PTR(-ENOMSG); } else if (kind == TCPOPT_NOP) { op++; continue; } if (opend - op < 2 || opend - op < op[1] || op[1] < 2) /* Something is wrong in the received header. * Follow the TCP stack's tcp_parse_options() * and just bail here. */ return ERR_PTR(-EFAULT); kind_len = op[1]; if (search_kind == kind) { if (!magic_len) return op; if (magic_len > kind_len - 2) return ERR_PTR(-ENOMSG); if (!memcmp(&op[2], magic, magic_len)) return op; } op += kind_len; } return ERR_PTR(-ENOMSG); } BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, void *, search_res, u32, len, u64, flags) { bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; const u8 *op, *opend, *magic, *search = search_res; u8 search_kind, search_len, copy_len, magic_len; int ret; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. */ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) return -EINVAL; search_kind = search[0]; search_len = search[1]; if (search_len > len || search_kind == TCPOPT_NOP || search_kind == TCPOPT_EOL) return -EINVAL; if (search_kind == TCPOPT_EXP || search_kind == 253) { /* 16 or 32 bit magic. +2 for kind and kind length */ if (search_len != 4 && search_len != 6) return -EINVAL; magic = &search[2]; magic_len = search_len - 2; } else { if (search_len) return -EINVAL; magic = NULL; magic_len = 0; } if (load_syn) { ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); if (ret < 0) return ret; opend = op + ret; op += sizeof(struct tcphdr); } else { if (!bpf_sock->skb || bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) /* This bpf_sock->op cannot call this helper */ return -EPERM; opend = bpf_sock->skb_data_end; op = bpf_sock->skb->data + sizeof(struct tcphdr); } op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, &eol); if (IS_ERR(op)) return PTR_ERR(op); copy_len = op[1]; ret = copy_len; if (copy_len > len) { ret = -ENOSPC; copy_len = len; } memcpy(search_res, op, copy_len); return ret; } static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .func = bpf_sock_ops_load_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, const void *, from, u32, len, u64, flags) { u8 new_kind, new_kind_len, magic_len = 0, *opend; const u8 *op, *new_op, *magic = NULL; struct sk_buff *skb; bool eol; if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) return -EPERM; if (len < 2 || flags) return -EINVAL; new_op = from; new_kind = new_op[0]; new_kind_len = new_op[1]; if (new_kind_len > len || new_kind == TCPOPT_NOP || new_kind == TCPOPT_EOL) return -EINVAL; if (new_kind_len > bpf_sock->remaining_opt_len) return -ENOSPC; /* 253 is another experimental kind */ if (new_kind == TCPOPT_EXP || new_kind == 253) { if (new_kind_len < 4) return -EINVAL; /* Match for the 2 byte magic also. * RFC 6994: the magic could be 2 or 4 bytes. * Hence, matching by 2 byte only is on the * conservative side but it is the right * thing to do for the 'search-for-duplication' * purpose. */ magic = &new_op[2]; magic_len = 2; } /* Check for duplication */ skb = bpf_sock->skb; op = skb->data + sizeof(struct tcphdr); opend = bpf_sock->skb_data_end; op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, &eol); if (!IS_ERR(op)) return -EEXIST; if (PTR_ERR(op) != -ENOMSG) return PTR_ERR(op); if (eol) /* The option has been ended. Treat it as no more * header option can be written. */ return -ENOSPC; /* No duplication found. Store the header option. */ memcpy(opend, from, new_kind_len); bpf_sock->remaining_opt_len -= new_kind_len; bpf_sock->skb_data_end += new_kind_len; return 0; } static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .func = bpf_sock_ops_store_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u32, len, u64, flags) { if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) return -EPERM; if (flags || len < 2) return -EINVAL; if (len > bpf_sock->remaining_opt_len) return -ENOSPC; bpf_sock->remaining_opt_len -= len; return 0; } static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .func = bpf_sock_ops_reserve_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; switch (tstamp_type) { case BPF_SKB_CLOCK_REALTIME: skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_REALTIME; break; case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; case BPF_SKB_CLOCK_TAI: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SYN_COOKIES BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th, u32, th_len) { u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; cookie = __cookie_v4_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th, u32, th_len) { #if IS_BUILTIN(CONFIG_IPV6) const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; cookie = __cookie_v6_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { .func = bpf_tcp_raw_check_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_BUILTIN(CONFIG_IPV6) if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { .func = bpf_tcp_raw_check_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; #endif /* CONFIG_SYN_COOKIES */ #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_clone_redirect: case BPF_FUNC_l3_csum_replace: case BPF_FUNC_l4_csum_replace: case BPF_FUNC_lwt_push_encap: case BPF_FUNC_lwt_seg6_action: case BPF_FUNC_lwt_seg6_adjust_srh: case BPF_FUNC_lwt_seg6_store_bytes: case BPF_FUNC_msg_pop_data: case BPF_FUNC_msg_pull_data: case BPF_FUNC_msg_push_data: case BPF_FUNC_skb_adjust_room: case BPF_FUNC_skb_change_head: case BPF_FUNC_skb_change_proto: case BPF_FUNC_skb_change_tail: case BPF_FUNC_skb_pull_data: case BPF_FUNC_skb_store_bytes: case BPF_FUNC_skb_vlan_pop: case BPF_FUNC_skb_vlan_push: case BPF_FUNC_store_hdr_opt: case BPF_FUNC_xdp_adjust_head: case BPF_FUNC_xdp_adjust_meta: case BPF_FUNC_xdp_adjust_tail: /* tail-called program could call any of the above */ case BPF_FUNC_tail_call: return true; default: return false; } } const struct bpf_func_proto bpf_event_output_data_proto __weak; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_bind_proto; default: return NULL; } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sock_addr_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; } default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_storage_get_proto __weak; const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; case BPF_FUNC_sk_cgroup_id: return &bpf_sk_cgroup_id_proto; case BPF_FUNC_sk_ancestor_cgroup_id: return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); } } static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_skb_vlan_push: return &bpf_skb_vlan_push_proto; case BPF_FUNC_skb_vlan_pop: return &bpf_skb_vlan_pop_proto; case BPF_FUNC_skb_change_proto: return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; case BPF_FUNC_skb_adjust_room: return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; case BPF_FUNC_redirect_peer: return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_set_hash: return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_skb_cgroup_classid: return &bpf_skb_cgroup_classid_proto; #endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_tc_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_tc_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_tc_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; case BPF_FUNC_skb_set_tstamp: return &bpf_skb_set_tstamp_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_proto; case BPF_FUNC_xdp_load_bytes: return &bpf_xdp_load_bytes_proto; case BPF_FUNC_xdp_store_bytes: return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; case BPF_FUNC_sk_lookup_tcp: return &bpf_xdp_sk_lookup_tcp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) /* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The * kfuncs are defined in two different modules, and we want to be able * to use them interchangeably with the same BTF type ID. Because modules * can't de-duplicate BTF IDs between each other, we need the type to be * referenced in the vmlinux BTF or the verifier will get confused about * the different types. So we add this dummy type reference which will * be included in vmlinux BTF, allowing both modules to refer to the * same type ID. */ BTF_TYPE_EMIT(struct nf_conn___init); #endif } const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_ops_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; case BPF_FUNC_store_hdr_opt: return &bpf_sock_ops_store_hdr_opt_proto; case BPF_FUNC_reserve_hdr_opt: return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; case BPF_FUNC_msg_redirect_hash: return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; case BPF_FUNC_msg_push_data: return &bpf_msg_push_data_proto; case BPF_FUNC_msg_pop_data: return &bpf_msg_pop_data_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sk_msg_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; case BPF_FUNC_skb_adjust_room: return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_lwt_push_encap: return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; #endif default: return lwt_out_func_proto(func_id, prog); } } static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): if (size != size_default) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, hwtstamp): if (type == BPF_WRITE || size != sizeof(__u64)) return false; break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; break; case offsetof(struct __sk_buff, sk): if (type == BPF_WRITE || size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; case offsetof(struct __sk_buff, tstamp_type): return false; case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { if (size != size_default) return false; } else { bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } } return true; } static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool cg_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, enum bpf_attach_type attach_type) { switch (off) { case offsetof(struct bpf_sock, bound_dev_if): case offsetof(struct bpf_sock, mark): case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; } case bpf_ctx_range(struct bpf_sock, src_ip4): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): switch (attach_type) { case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range(struct bpf_sock, src_port): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } } read_only: return access_type == BPF_READ; full_access: return true; } bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range_till(struct bpf_sock, type, priority): return false; default: return bpf_sock_is_valid_access(off, size, type, info); } } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_sock, state): case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock, dst_port): field_size = size == size_default ? size_default : sizeof_field(struct bpf_sock, dst_port); bpf_ctx_record_field_size(info, field_size); return bpf_ctx_narrow_access_ok(off, size, field_size); case offsetofend(struct bpf_sock, dst_port) ... offsetof(struct bpf_sock, dst_ip4) - 1: return false; } return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_sock_is_valid_access(off, size, type, info)) return false; return __sock_filter_check_attach_type(off, type, prog->expected_attach_type); } static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Neither direct read nor direct write requires any preliminary * action. */ return 0; } static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; if (!direct_write) return 0; /* if (!skb->cloned) * goto start; * * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); /* ret = bpf_skb_pull_data(skb, 0); */ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_pull_data); /* if (!ret) * goto restore; * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); /* start: */ *insn++ = prog->insnsi[0]; return insn - insn_buf; } static int bpf_gen_ld_abs(const struct bpf_insn *orig, struct bpf_insn *insn_buf) { bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } /* We're guaranteed here that CTX is in R6. */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); break; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); *insn++ = BPF_EXIT_INSN(); return insn - insn_buf; } static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); } static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, queue_mapping): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog * has used __sk_buff->tstamp_type or not. * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); } DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) return false; if (off % size != 0) return false; if (size != sizeof(__u32)) return false; return true; } static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (prog->expected_attach_type != BPF_XDP_DEVMAP) { switch (off) { case offsetof(struct xdp_md, egress_ifindex): return false; } } if (type == BPF_WRITE) { if (bpf_prog_is_offloaded(prog->aux)) { switch (off) { case offsetof(struct xdp_md, rx_queue_index): return __is_valid_xdp_access(off, size); } } return false; } else { switch (off) { case offsetof(struct xdp_md, data_meta): case offsetof(struct xdp_md, data): case offsetof(struct xdp_md, data_end): if (info->is_ldsx) return false; } } switch (off) { case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return __is_valid_xdp_access(off, size); } void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A"); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_addr)) return false; if (off % size != 0) return false; /* Disallow access to fields not belonging to the attach type's address * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; default: return false; } break; case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; } break; } switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (size != size_default) return false; } break; case offsetof(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; default: if (type == BPF_READ) { if (size != size_default) return false; } else { return false; } } return true; } static bool sock_ops_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_ops)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sock_ops, reply): case offsetof(struct bpf_sock_ops, sk_txhash): if (size != size_default) return false; break; default: return false; } } else { switch (off) { case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received, bytes_acked): if (size != sizeof(__u64)) return false; break; case offsetof(struct bpf_sock_ops, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; case offsetof(struct bpf_sock_ops, skb_data): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case offsetof(struct bpf_sock_ops, skb_data_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case offsetof(struct bpf_sock_ops, skb_hwtstamp): if (size != sizeof(__u64)) return false; break; default: if (size != size_default) return false; break; } } return true; } static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); } static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, mark): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool sk_msg_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; if (size != sizeof(__u64)) return false; break; case offsetof(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; if (size != sizeof(__u64)) return false; break; case offsetof(struct sk_msg_md, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct sk_msg_md, remote_port): case bpf_ctx_range(struct sk_msg_md, local_port): case bpf_ctx_range(struct sk_msg_md, size): if (size != sizeof(__u32)) return false; break; default: return false; } return true; } static bool flow_dissector_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_FLOW_KEYS; return true; default: return false; } } static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data)); break; case offsetof(struct __sk_buff, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data_end)); break; case offsetof(struct __sk_buff, flow_keys): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, flow_keys)); break; } return insn - insn_buf; } static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); #else BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); #endif return insn; } static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), dst_reg, skb_reg, offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif return insn; } static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, read skb->tstamp as is if tstamp_type_access is true. */ if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* check if ingress mask bits is set */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); *insn++ = BPF_JMP_A(4); *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); *insn++ = BPF_JMP_A(2); /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); *insn++ = BPF_JMP_A(1); } #endif *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, offsetof(struct sk_buff, tstamp)); return insn; } static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* Writing __sk_buff->tstamp as ingress, goto <clear> */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); /* <clear>: skb->tstamp_type */ *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif /* <store>: skb->tstamp = tstamp */ *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_DW | BPF_MEM, skb_reg, value_reg, offsetof(struct sk_buff, tstamp), si->imm); return insn; } #define BPF_EMIT_STORE(size, si, off) \ BPF_RAW_INSN(BPF_CLASS((si)->code) | (size) | BPF_MEM, \ (si)->dst_reg, (si)->src_reg, (off), (si)->imm) static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, len, 4, target_size)); break; case offsetof(struct __sk_buff, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, protocol, 2, target_size)); break; case offsetof(struct __sk_buff, vlan_proto): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_proto, 2, target_size)); break; case offsetof(struct __sk_buff, priority): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, priority, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, skb_iif, 4, target_size)); break; case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; case offsetof(struct __sk_buff, hash): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, hash, 4, target_size)); break; case offsetof(struct __sk_buff, mark): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, mark, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); break; case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); #endif break; case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ break; } if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } break; case offsetof(struct __sk_buff, vlan_present): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_all, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_tci, 2, target_size)); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, off); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_meta): off = si->off; off -= offsetof(struct __sk_buff, data_meta); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_meta); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, napi_id, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_family, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_daddr, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, 4, target_size)); break; case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_dport, 2, target_size)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct __sk_buff, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) insn = bpf_convert_tstamp_write(prog, si, insn); else insn = bpf_convert_tstamp_read(prog, si, insn); break; case offsetof(struct __sk_buff, tstamp_type): insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; case offsetof(struct __sk_buff, gso_size): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_size, 2, target_size)); break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; case offsetof(struct __sk_buff, hwtstamp): BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); break; } return insn - insn_buf; } u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_bound_dev_if)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, mark): BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_mark)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); break; case offsetof(struct bpf_sock, priority): BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_priority)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); break; case offsetof(struct bpf_sock, family): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_family), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, sizeof_field(struct sock_common, skc_family), target_size)); break; case offsetof(struct bpf_sock, type): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_type), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_type, sizeof_field(struct sock, sk_type), target_size)); break; case offsetof(struct bpf_sock, protocol): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_protocol), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_protocol, sizeof_field(struct sock, sk_protocol), target_size)); break; case offsetof(struct bpf_sock, src_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; case offsetof(struct bpf_sock, dst_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, sizeof_field(struct sock_common, skc_daddr), target_size)); break; case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, src_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else (void)off; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, dst_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); *target_size = 4; #endif break; case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, sizeof_field(struct sock_common, skc_num), target_size)); break; case offsetof(struct bpf_sock, dst_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, sizeof_field(struct sock_common, skc_dport), target_size)); break; case offsetof(struct bpf_sock, state): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, sizeof_field(struct sock_common, skc_state), target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_rx_queue_mapping, sizeof_field(struct sock, sk_rx_queue_mapping), target_size)); *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); #else *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); *target_size = 2; #endif break; } return insn - insn_buf; } static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_meta): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_meta)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; case offsetof(struct xdp_md, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct xdp_md, rx_queue_index): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, queue_index)); break; case offsetof(struct xdp_md, egress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, txq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_txq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; } return insn - insn_buf; } /* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of * context Structure, F is Field in context structure that contains a pointer * to Nested Structure of type NS that has the field NF. * * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make * sure that SIZE is not greater than actual size of S.F.NF. * * If offset OFF is provided, the load happens from that offset relative to * offset of NF. */ #define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \ do { \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \ si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) #define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \ BPF_FIELD_SIZEOF(NS, NF), 0) /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation. * * In addition it uses Temporary Field TF (member of struct S) as the 3rd * "register" since two registers available in convert_ctx_access are not * enough: we can't override neither SRC, since it contains value to store, nor * DST since it contains pointer to context that may be used by later * instructions. But we need a temporary place to save pointer to nested * structure whose field we want to store to. */ #define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF) \ do { \ int tmp_reg = BPF_REG_9; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \ offsetof(S, TF)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_RAW_INSN(SIZE | BPF_MEM | BPF_CLASS(si->code), \ tmp_reg, si->src_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF, \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ offsetof(S, TF)); \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \ TF) \ do { \ if (type == BPF_WRITE) { \ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, \ OFF, TF); \ } else { \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, SIZE, OFF); \ } \ } while (0) static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr, uaddr, sa_family); break; case offsetof(struct bpf_sock_addr, user_ip4): SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in, uaddr, sin_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, user_ip6[0]); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, user_port): /* To get port we need to know sa_family first and then treat * sockaddr as either sockaddr_in or sockaddr_in6. * Though we can simplify since port field has same offset and * size in both structures. * Here we check this invariant and use just one of the * structures if it's true. */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); /* Account for sin6_port being smaller than user_port. */ port_size = min(port_size, BPF_LDST_BYTES(si)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_family); break; case offsetof(struct bpf_sock_addr, type): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): /* Treat t_ctx as struct in_addr for msg_src_ip4. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in_addr, t_ctx, s_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_addr_kern, sk)); break; } return insn - insn_buf; } static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_SK() \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) /* Helper macro for adding write access to tcp_sock or sock fields. * The macro is called with two registers, dst_reg which contains a pointer * to ctx (context) and src_reg which contains the value that should be * stored. However, we need an additional register since we cannot overwrite * dst_reg because it may be used later in the program. * Instead we "borrow" one of the other register. We first save its value * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore * it at the end of the macro. */ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_RAW_INSN(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD) | \ BPF_MEM | BPF_CLASS(si->code), \ reg, si->src_reg, \ offsetof(OBJ, OBJ_FIELD), \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } while (0) #define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ do { \ if (TYPE == BPF_WRITE) \ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ else \ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) switch (si->off) { case offsetof(struct bpf_sock_ops, op): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, op), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, op)); break; case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, replylong[0]); off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, off); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct bpf_sock_ops, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct bpf_sock_ops, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct bpf_sock_ops, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct bpf_sock_ops, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct bpf_sock_ops, is_fullsock): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, is_fullsock), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, is_fullsock)); break; case offsetof(struct bpf_sock_ops, state): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_state)); break; case offsetof(struct bpf_sock_ops, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); break; case offsetof(struct bpf_sock_ops, srtt_us): SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); break; case offsetof(struct bpf_sock_ops, snd_ssthresh): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); break; case offsetof(struct bpf_sock_ops, rcv_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); break; case offsetof(struct bpf_sock_ops, snd_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); break; case offsetof(struct bpf_sock_ops, snd_una): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); break; case offsetof(struct bpf_sock_ops, mss_cache): SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); break; case offsetof(struct bpf_sock_ops, ecn_flags): SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); break; case offsetof(struct bpf_sock_ops, rate_delivered): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); break; case offsetof(struct bpf_sock_ops, rate_interval_us): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); break; case offsetof(struct bpf_sock_ops, packets_out): SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); break; case offsetof(struct bpf_sock_ops, retrans_out): SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); break; case offsetof(struct bpf_sock_ops, total_retrans): SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); break; case offsetof(struct bpf_sock_ops, segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); break; case offsetof(struct bpf_sock_ops, data_segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); break; case offsetof(struct bpf_sock_ops, segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); break; case offsetof(struct bpf_sock_ops, data_segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); break; case offsetof(struct bpf_sock_ops, lost_out): SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); break; case offsetof(struct bpf_sock_ops, sacked_out): SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); break; case offsetof(struct bpf_sock_ops, bytes_received): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); break; case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; case offsetof(struct bpf_sock_ops, skb_data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb_data_end)); break; case offsetof(struct bpf_sock_ops, skb_data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct bpf_sock_ops, skb_len): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): off = offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, tcp_flags); *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, tcp_flags), si->dst_reg, si->dst_reg, off); break; case offsetof(struct bpf_sock_ops, skb_hwtstamp): { struct bpf_insn *jmp_on_null_skb; *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); /* Reserve one insn to test skb == NULL */ jmp_on_null_skb = insn++; insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, insn - jmp_on_null_skb - 1); break; } } return insn - insn_buf; } /* data_end = skb->data + skb_headlen() */ static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { int reg; int temp_reg_off = offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, temp_reg); if (si->src_reg == si->dst_reg) { /* We need an extra register, choose and save a register. */ reg = BPF_REG_9; if (si->src_reg == reg || si->dst_reg == reg) reg--; if (si->src_reg == reg || si->dst_reg == reg) reg--; *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); } else { reg = si->dst_reg; } /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); /* reg = skb->data + skb->len */ *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); /* reg = skb->data + skb->len - skb->data_len */ *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); if (si->src_reg == si->dst_reg) { /* Restore the saved register */ *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); *insn++ = BPF_MOV64_REG(si->dst_reg, reg); *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); } return insn; } static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct sk_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #if IS_ENABLED(CONFIG_IPV6) int off; #endif /* convert ctx uses the fact sg element is first in struct */ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0); switch (si->off) { case offsetof(struct sk_msg_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct sk_msg_md, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct sk_msg_md, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct sk_msg_md, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct sk_msg_md, size): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size), si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; case offsetof(struct sk_msg_md, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_in_verifier_ops = { .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_in_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_out_verifier_ops = { .get_func_proto = lwt_out_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { .get_func_proto = lwt_seg6local_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { }; const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { }; const struct bpf_verifier_ops cg_sock_addr_verifier_ops = { .get_func_proto = sock_addr_func_proto, .is_valid_access = sock_addr_is_valid_access, .convert_ctx_access = sock_addr_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_addr_prog_ops = { }; const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; const struct bpf_prog_ops sock_ops_prog_ops = { }; const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; const struct bpf_prog_ops sk_skb_prog_ops = { }; const struct bpf_verifier_ops sk_msg_verifier_ops = { .get_func_proto = sk_msg_func_proto, .is_valid_access = sk_msg_is_valid_access, .convert_ctx_access = sk_msg_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops sk_msg_prog_ops = { }; const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; struct sk_filter *filter; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; sockopt_lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) goto out; /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. eBPF programs that * have no original program cannot be dumped through this. */ ret = -EACCES; fprog = filter->prog->orig_prog; if (!fprog) goto out; ret = fprog->len; if (!len) /* User space only enquires number of filter blocks. */ goto out; ret = -EINVAL; if (len < fprog->len) goto out; ret = -EFAULT; if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number * of filter blocks. */ ret = fprog->len; out: sockopt_release_sock(sk); return ret; } #ifdef CONFIG_INET static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; reuse_kern->bind_inany = reuse->bind_inany; } struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; else return ERR_PTR(-ECONNREFUSED); } BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. * * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ err = is_sockarray ? -ENOENT : -EINVAL; goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) { err = -EPROTOTYPE; } else if (sk->sk_family != selected_sk->sk_family) { err = -EAFNOSUPPORT; } else { /* Catch all. Likely bound to a different sockaddr. */ err = -EBADFD; } goto error; } reuse_kern->selected_sk = selected_sk; return 0; error: /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ if (sk_is_refcounted(selected_sk)) sock_put(selected_sk); return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { .func = sk_select_reuseport, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(sk_reuseport_load_bytes, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len) { return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); } static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { .func = sk_reuseport_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(sk_reuseport_load_bytes_relative, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len, u32, start_header) { return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, len, start_header); } static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { .func = sk_reuseport_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_reuseport_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sk_select_reuseport: return &sk_select_reuseport_proto; case BPF_FUNC_skb_load_bytes: return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sk_reuseport_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const u32 size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct sk_reuseport_md) || off % size || type != BPF_READ) return false; switch (off) { case offsetof(struct sk_reuseport_md, data): info->reg_type = PTR_TO_PACKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, data_end): info->reg_type = PTR_TO_PACKET_END; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, hash): return size == size_default; case offsetof(struct sk_reuseport_md, sk): info->reg_type = PTR_TO_SOCKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, migrating_sk): info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; return size == sizeof(__u64); /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: return false; } } #define SK_REUSEPORT_LOAD_FIELD(F) ({ \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) #define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sk_buff, \ skb, \ SKB_FIELD) #define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sock, \ sk, \ SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct sk_reuseport_md, data): SK_REUSEPORT_LOAD_SKB_FIELD(data); break; case offsetof(struct sk_reuseport_md, len): SK_REUSEPORT_LOAD_SKB_FIELD(len); break; case offsetof(struct sk_reuseport_md, eth_protocol): SK_REUSEPORT_LOAD_SKB_FIELD(protocol); break; case offsetof(struct sk_reuseport_md, ip_protocol): SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): SK_REUSEPORT_LOAD_FIELD(data_end); break; case offsetof(struct sk_reuseport_md, hash): SK_REUSEPORT_LOAD_FIELD(hash); break; case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; case offsetof(struct sk_reuseport_md, sk): SK_REUSEPORT_LOAD_FIELD(sk); break; case offsetof(struct sk_reuseport_md, migrating_sk): SK_REUSEPORT_LOAD_FIELD(migrating_sk); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_reuseport_verifier_ops = { .get_func_proto = sk_reuseport_func_proto, .is_valid_access = sk_reuseport_is_valid_access, .convert_ctx_access = sk_reuseport_convert_ctx_access, }; const struct bpf_prog_ops sk_reuseport_prog_ops = { }; DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); EXPORT_SYMBOL(bpf_sk_lookup_enabled); BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, struct sock *, sk, u64, flags) { if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | BPF_SK_LOOKUP_F_NO_REUSEPORT))) return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) return -EPROTOTYPE; if (sk && sk->sk_family != ctx->family && (sk->sk_family == AF_INET || ipv6_only_sock(sk))) return -EAFNOSUPPORT; if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) return -EEXIST; /* Select socket as lookup result */ ctx->selected_sk = sk; ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; return 0; } static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { .func = bpf_sk_lookup_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_assign: return &bpf_sk_lookup_assign_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static bool sk_lookup_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) return false; if (off % size != 0) return false; if (type != BPF_READ) return false; switch (off) { case offsetof(struct bpf_sk_lookup, sk): info->reg_type = PTR_TO_SOCKET_OR_NULL; return size == sizeof(__u64); case bpf_ctx_range(struct bpf_sk_lookup, family): case bpf_ctx_range(struct bpf_sk_lookup, protocol): case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); case bpf_ctx_range(struct bpf_sk_lookup, remote_port): /* Allow 4-byte access to 2-byte field for backward compatibility */ if (size == sizeof(__u32)) return true; bpf_ctx_record_field_size(info, sizeof(__be16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16)); case offsetofend(struct bpf_sk_lookup, remote_port) ... offsetof(struct bpf_sk_lookup, local_ip4) - 1: /* Allow access to zero padding for backward compatibility */ bpf_ctx_record_field_size(info, sizeof(__u16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16)); default: return false; } } static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sk_lookup, sk): *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, selected_sk)); break; case offsetof(struct bpf_sk_lookup, family): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, family, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, protocol, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, remote_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.saddr, 4, target_size)); break; case offsetof(struct bpf_sk_lookup, local_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.daddr, 4, target_size)); break; case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.saddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.daddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case offsetof(struct bpf_sk_lookup, remote_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, sport, 2, target_size)); break; case offsetofend(struct bpf_sk_lookup, remote_port): *target_size = 2; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); break; case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, ingress_ifindex, 4, target_size)); break; } return insn - insn_buf; } const struct bpf_prog_ops sk_lookup_prog_ops = { .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { .get_func_proto = sk_lookup_func_proto, .is_valid_access = sk_lookup_is_valid_access, .convert_ctx_access = sk_lookup_convert_ctx_access, }; #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } BTF_ID_LIST_GLOBAL(btf_sock_ids, MAX_BTF_SOCK_TYPE) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { /* BTF types for tcp_timewait_sock and inet_timewait_sock are not * generated if CONFIG_INET=n. Trigger an explicit generation here. */ BTF_TYPE_EMIT(struct inet_timewait_sock); BTF_TYPE_EMIT(struct tcp_timewait_sock); #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) { /* udp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) { /* unix_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct unix_sock); if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { .func = bpf_skc_to_unix_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], }; BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk) { BTF_TYPE_EMIT(struct mptcp_sock); return (unsigned long)bpf_mptcp_sock_from_subflow(sk); } const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = { .func = bpf_skc_to_mptcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP], }; BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); } BTF_ID_LIST(bpf_sock_from_file_btf_ids) BTF_ID(struct, socket) BTF_ID(struct, file) const struct bpf_func_proto bpf_sock_from_file_proto = { .func = bpf_sock_from_file, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = &bpf_sock_from_file_btf_ids[0], .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], }; static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; switch (func_id) { case BPF_FUNC_skc_to_tcp6_sock: func = &bpf_skc_to_tcp6_sock_proto; break; case BPF_FUNC_skc_to_tcp_sock: func = &bpf_skc_to_tcp_sock_proto; break; case BPF_FUNC_skc_to_tcp_timewait_sock: func = &bpf_skc_to_tcp_timewait_sock_proto; break; case BPF_FUNC_skc_to_tcp_request_sock: func = &bpf_skc_to_tcp_request_sock_proto; break; case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; case BPF_FUNC_skc_to_mptcp_sock: func = &bpf_skc_to_mptcp_sock_proto; break; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; } __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)s; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); return 0; } __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct xdp_buff *xdp = (struct xdp_buff *)x; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); return 0; } __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, const u8 *sun_path, u32 sun_path__sz) { struct sockaddr_un *un; if (sa_kern->sk->sk_family != AF_UNIX) return -EINVAL; /* We do not allow changing the address to unnamed or larger than the * maximum allowed address size for a unix sockaddr. */ if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) return -EINVAL; un = (struct sockaddr_un *)sa_kern->uaddr; memcpy(un->sun_path, sun_path, sun_path__sz); sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; return 0; } __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, struct bpf_tcp_req_attrs *attrs, int attrs__sz) { #if IS_ENABLED(CONFIG_SYN_COOKIES) struct sk_buff *skb = (struct sk_buff *)s; const struct request_sock_ops *ops; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; struct net *net; __u16 min_mss; u32 tsoff = 0; if (attrs__sz != sizeof(*attrs) || attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2]) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EINVAL; net = dev_net(skb->dev); if (net != sock_net(sk)) return -ENETUNREACH; switch (skb->protocol) { case htons(ETH_P_IP): ops = &tcp_request_sock_ops; min_mss = 536; break; #if IS_BUILTIN(CONFIG_IPV6) case htons(ETH_P_IPV6): ops = &tcp6_request_sock_ops; min_mss = IPV6_MIN_MTU - 60; break; #endif default: return -EINVAL; } if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN || sk_is_mptcp(sk)) return -EINVAL; if (attrs->mss < min_mss) return -EINVAL; if (attrs->wscale_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) return -EINVAL; if (attrs->snd_wscale > TCP_MAX_WSCALE || attrs->rcv_wscale > TCP_MAX_WSCALE) return -EINVAL; } if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return -EINVAL; if (attrs->tstamp_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return -EINVAL; tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns()); } req = inet_reqsk_alloc(ops, sk, false); if (!req) return -ENOMEM; ireq = inet_rsk(req); treq = tcp_rsk(req); req->rsk_listener = sk; req->syncookie = 1; req->mss = attrs->mss; req->ts_recent = attrs->rcv_tsval; ireq->snd_wscale = attrs->snd_wscale; ireq->rcv_wscale = attrs->rcv_wscale; ireq->tstamp_ok = !!attrs->tstamp_ok; ireq->sack_ok = !!attrs->sack_ok; ireq->wscale_ok = !!attrs->wscale_ok; ireq->ecn_ok = !!attrs->ecn_ok; treq->req_usec_ts = !!attrs->usec_ts_ok; treq->ts_off = tsoff; skb_orphan(skb); skb->sk = req_to_sk(req); skb->destructor = sock_pfree; return 0; #else return -EOPNOTSUPP; #endif } __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) { struct sk_buff *skb; if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) return -EOPNOTSUPP; if (flags) return -EINVAL; skb = skops->skb; skb_shinfo(skb)->tx_flags |= SKBTX_BPF; TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF; skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; return 0; } __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; int err; err = bpf_dynptr_from_skb(skb, flags, ptr__uninit); if (err) return err; bpf_dynptr_set_rdonly(ptr); return 0; } BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops) BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops) static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, }; static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_xdp, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_addr, }; static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_tcp_reqsk, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_ops, }; static int __init bpf_kfunc_init(void) { int ret; ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops); } late_initcall(bpf_kfunc_init); __bpf_kfunc_start_defs(); /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. * * The function expects a non-NULL pointer to a socket, and invokes the * protocol specific socket destroy handlers. * * The helper can only be called from BPF contexts that have acquired the socket * locks. * * Parameters: * @sock: Pointer to socket to be destroyed * * Return: * On error, may return EPROTONOSUPPORT, EINVAL. * EPROTONOSUPPORT if protocol specific destroy handler is not supported. * 0 otherwise */ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) { struct sock *sk = (struct sock *)sock; /* The locking semantics that allow for synchronous execution of the * destroy handlers are only supported for TCP and UDP. * Supporting protocols will need to acquire sock lock in the BPF context * prior to invoking this kfunc. */ if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_UDP)) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, ECONNABORTED); } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) && prog->expected_attach_type != BPF_TRACE_ITER) return -EACCES; return 0; } static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_sk_iter_kfunc_ids, .filter = tracing_iter_filter, }; static int init_subsystem(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); } late_initcall(init_subsystem); |
| 12 1 2 2 1 3 2 2 15 17 4 1 14 3 12 14 7 12 7 11 1 2 12 6 2 1 4 64 15 3 3 59 1 57 22 16 13 3 2 9 2 3 11 18 2 16 14 14 14 149 74 3 1 1 1 36 3 2 3 4 5 2 2 2 16 2 3 2 3 2 1 1 12 4 2 2 3 8 9 7 2 3 6 1 53 1 4 3 1 7 5 117 10 1 50 2 60 60 2 63 63 63 16 1 1 14 13 13 2 2 10 6 68 68 68 68 60 60 60 20 20 1 19 66 57 56 56 56 56 2 57 57 57 57 16 30 14 5 6 30 10 45 23 4 7 1 12 46 7 39 56 56 39 1 1 1 1 1 3 2 1 1 1 4 27 27 27 5 3 2 17 3 14 14 16 1 15 3 11 2 4 5 12 11 4 1 1 3 1 1 1 1 15 15 15 2 9 2 9 52 1 13 12 1 10 3 12 1 4 5 5 14 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic PPP layer for Linux. * * Copyright 1999-2002 Paul Mackerras. * * The generic PPP layer handles the PPP network interfaces, the * /dev/ppp device, packet and VJ compression, and multilink. * It talks to PPP `channels' via the interface defined in * include/linux/ppp_channel.h. Channels provide the basic means for * sending and receiving PPP frames on some kind of communications * channel. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20041108== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/filter.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/rwsem.h> #include <linux/stddef.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/unaligned.h> #include <net/netdev_lock.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #define PPP_VERSION "2.4.2" /* * Network protocols we support. */ #define NP_IP 0 /* Internet Protocol V4 */ #define NP_IPV6 1 /* Internet Protocol V6 */ #define NP_IPX 2 /* IPX protocol */ #define NP_AT 3 /* Appletalk protocol */ #define NP_MPLS_UC 4 /* MPLS unicast */ #define NP_MPLS_MC 5 /* MPLS multicast */ #define NUM_NP 6 /* Number of NPs. */ #define MPHDRLEN 6 /* multilink protocol header length */ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 #define PPP_LCP_HDRLEN 4 /* The filter instructions generated by libpcap are constructed * assuming a four-byte PPP header on each packet, where the last * 2 bytes are the protocol field defined in the RFC and the first * byte of the first 2 bytes indicates the direction. * The second byte is currently unused, but we still need to initialize * it to prevent crafted BPF programs from reading them which would * cause reading of uninitialized data. */ #define PPP_FILTER_OUTBOUND_TAG 0x0100 #define PPP_FILTER_INBOUND_TAG 0x0000 /* * An instance of /dev/ppp can be associated with either a ppp * interface unit or a ppp channel. In both cases, file->private_data * points to one of these. */ struct ppp_file { enum { INTERFACE=1, CHANNEL } kind; struct sk_buff_head xq; /* pppd transmit queue */ struct sk_buff_head rq; /* receive queue for pppd */ wait_queue_head_t rwait; /* for poll on reading /dev/ppp */ refcount_t refcnt; /* # refs (incl /dev/ppp attached) */ int hdrlen; /* space to leave for headers */ int index; /* interface unit / channel number */ int dead; /* unit/channel has been shut down */ }; #define PF_TO_X(pf, X) container_of(pf, X, file) #define PF_TO_PPP(pf) PF_TO_X(pf, struct ppp) #define PF_TO_CHANNEL(pf) PF_TO_X(pf, struct channel) /* * Data structure describing one ppp unit. * A ppp unit corresponds to a ppp network interface device * and represents a multilink bundle. * It can have 0 or more ppp channels connected to it. */ struct ppp { struct ppp_file file; /* stuff for read/write/poll 0 */ struct file *owner; /* file that owns this unit 48 */ struct list_head channels; /* list of attached channels 4c */ int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ unsigned int rstate; /* receive state bits 6c */ int debug; /* debug flags 70 */ struct slcompress *vj; /* state for VJ header compression */ enum NPmode npmode[NUM_NP]; /* what to do with each net proto 78 */ struct sk_buff *xmit_pending; /* a packet ready to go out 88 */ struct compressor *xcomp; /* transmit packet compressor 8c */ void *xc_state; /* its internal state 90 */ struct compressor *rcomp; /* receive decompressor 94 */ void *rc_state; /* its internal state 98 */ unsigned long last_xmit; /* jiffies when last pkt sent 9c */ unsigned long last_recv; /* jiffies when last pkt rcvd a0 */ struct net_device *dev; /* network interface device a4 */ int closing; /* is device closing down? a8 */ #ifdef CONFIG_PPP_MULTILINK int nxchan; /* next channel to send something on */ u32 nxseq; /* next sequence number to send */ int mrru; /* MP: max reconst. receive unit */ u32 nextseq; /* MP: seq no of next packet */ u32 minseq; /* MP: min of most recent seqnos */ struct sk_buff_head mrq; /* MP: receive reconstruction queue */ #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER struct bpf_prog *pass_filter; /* filter for packets to pass */ struct bpf_prog *active_filter; /* filter for pkts to reset idle */ #endif /* CONFIG_PPP_FILTER */ struct net *ppp_net; /* the net we belong to */ }; /* * Bits in flags: SC_NO_TCP_CCID, SC_CCP_OPEN, SC_CCP_UP, SC_LOOP_TRAFFIC, * SC_MULTILINK, SC_MP_SHORTSEQ, SC_MP_XSHORTSEQ, SC_COMP_TCP, SC_REJ_COMP_TCP, * SC_MUST_COMP * Bits in rstate: SC_DECOMP_RUN, SC_DC_ERROR, SC_DC_FERROR. * Bits in xstate: SC_COMP_RUN */ #define SC_FLAG_BITS (SC_NO_TCP_CCID|SC_CCP_OPEN|SC_CCP_UP|SC_LOOP_TRAFFIC \ |SC_MULTILINK|SC_MP_SHORTSEQ|SC_MP_XSHORTSEQ \ |SC_COMP_TCP|SC_REJ_COMP_TCP|SC_MUST_COMP) /* * Private data structure for each channel. * This includes the data structure used for multilink. */ struct channel { struct ppp_file file; /* stuff for read/write/poll */ struct list_head list; /* link in all/new_channels list */ struct ppp_channel *chan; /* public channel data structure */ struct rw_semaphore chan_sem; /* protects `chan' during chan ioctl */ spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ netns_tracker ns_tracker; struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ u32 lastseq; /* MP: last sequence # received */ int speed; /* speed of the corresponding ppp channel*/ #endif /* CONFIG_PPP_MULTILINK */ }; struct ppp_config { struct file *file; s32 unit; bool ifname_is_set; }; /* * SMP locking issues: * Both the ppp.rlock and ppp.wlock locks protect the ppp.channels * list and the ppp.n_channels field, you need to take both locks * before you modify them. * The lock ordering is: channel.upl -> ppp.wlock -> ppp.rlock -> * channel.downl. */ static DEFINE_MUTEX(ppp_mutex); static atomic_t ppp_unit_count = ATOMIC_INIT(0); static atomic_t channel_count = ATOMIC_INIT(0); /* per-net private data for this module */ static unsigned int ppp_net_id __read_mostly; struct ppp_net { /* units to ppp mapping */ struct idr units_idr; /* * all_ppp_mutex protects the units_idr mapping. * It also ensures that finding a ppp unit in the units_idr * map and updating its file.refcnt field is atomic. */ struct mutex all_ppp_mutex; /* channels */ struct list_head all_channels; struct list_head new_channels; int last_channel_index; /* * all_channels_lock protects all_channels and * last_channel_index, and the atomicity of find * a channel and updating its file.refcnt field. */ spinlock_t all_channels_lock; }; /* Get the PPP protocol number from a skb */ #define PPP_PROTO(skb) get_unaligned_be16((skb)->data) /* We limit the length of ppp->file.rq to this (arbitrary) value */ #define PPP_MAX_RQLEN 32 /* * Maximum number of multilink fragments queued up. * This has to be large enough to cope with the maximum latency of * the slowest channel relative to the others. Strictly it should * depend on the number of channels and their characteristics. */ #define PPP_MP_MAX_QLEN 128 /* Multilink header bits. */ #define B 0x80 /* this fragment begins a packet */ #define E 0x40 /* this fragment ends a packet */ /* Compare multilink sequence numbers (assumed to be 32 bits wide) */ #define seq_before(a, b) ((s32)((a) - (b)) < 0) #define seq_after(a, b) ((s32)((a) - (b)) > 0) /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_receive_error(struct ppp *ppp); static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb); #ifdef CONFIG_PPP_MULTILINK static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_mp_reconstruct(struct ppp *ppp); static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb); #endif /* CONFIG_PPP_MULTILINK */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data); static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound); static void ppp_ccp_closed(struct ppp *ppp); static struct compressor *find_compressor(int type); static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st); static int ppp_create_interface(struct net *net, struct file *file, int *unit); static void init_ppp_file(struct ppp_file *pf, int kind); static void ppp_destroy_interface(struct ppp *ppp); static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit); static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; static const struct class ppp_class = { .name = "ppp", }; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) { return net_generic(net, ppp_net_id); } /* Translates a PPP protocol number to a NP index (NP == network protocol) */ static inline int proto_to_npindex(int proto) { switch (proto) { case PPP_IP: return NP_IP; case PPP_IPV6: return NP_IPV6; case PPP_IPX: return NP_IPX; case PPP_AT: return NP_AT; case PPP_MPLS_UC: return NP_MPLS_UC; case PPP_MPLS_MC: return NP_MPLS_MC; } return -EINVAL; } /* Translates an NP index into a PPP protocol number */ static const int npindex_to_proto[NUM_NP] = { PPP_IP, PPP_IPV6, PPP_IPX, PPP_AT, PPP_MPLS_UC, PPP_MPLS_MC, }; /* Translates an ethertype into an NP index */ static inline int ethertype_to_npindex(int ethertype) { switch (ethertype) { case ETH_P_IP: return NP_IP; case ETH_P_IPV6: return NP_IPV6; case ETH_P_IPX: return NP_IPX; case ETH_P_PPPTALK: case ETH_P_ATALK: return NP_AT; case ETH_P_MPLS_UC: return NP_MPLS_UC; case ETH_P_MPLS_MC: return NP_MPLS_MC; } return -1; } /* Translates an NP index into an ethertype */ static const int npindex_to_ethertype[NUM_NP] = { ETH_P_IP, ETH_P_IPV6, ETH_P_IPX, ETH_P_PPPTALK, ETH_P_MPLS_UC, ETH_P_MPLS_MC, }; /* * Locking shorthand. */ #define ppp_xmit_lock(ppp) spin_lock_bh(&(ppp)->wlock) #define ppp_xmit_unlock(ppp) spin_unlock_bh(&(ppp)->wlock) #define ppp_recv_lock(ppp) spin_lock_bh(&(ppp)->rlock) #define ppp_recv_unlock(ppp) spin_unlock_bh(&(ppp)->rlock) #define ppp_lock(ppp) do { ppp_xmit_lock(ppp); \ ppp_recv_lock(ppp); } while (0) #define ppp_unlock(ppp) do { ppp_recv_unlock(ppp); \ ppp_xmit_unlock(ppp); } while (0) /* * /dev/ppp device routines. * The /dev/ppp device is used by pppd to control the ppp unit. * It supports the read, write, ioctl and poll functions. * Open instances of /dev/ppp can be in one of three states: * unattached, attached to a ppp unit, or attached to a ppp channel. */ static int ppp_open(struct inode *inode, struct file *file) { /* * This could (should?) be enforced by the permissions on /dev/ppp. */ if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN)) return -EPERM; return 0; } static int ppp_release(struct inode *unused, struct file *file) { struct ppp_file *pf = file->private_data; struct ppp *ppp; if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); if (file == ppp->owner) unregister_netdevice(ppp->dev); rtnl_unlock(); } if (refcount_dec_and_test(&pf->refcnt)) { switch (pf->kind) { case INTERFACE: ppp_destroy_interface(PF_TO_PPP(pf)); break; case CHANNEL: ppp_destroy_channel(PF_TO_CHANNEL(pf)); break; } } } return 0; } static ssize_t ppp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; DECLARE_WAITQUEUE(wait, current); ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; struct iov_iter to; ret = count; if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); skb = skb_dequeue(&pf->rq); if (skb) break; ret = 0; if (pf->dead) break; if (pf->kind == INTERFACE) { /* * Return 0 (EOF) on an interface that has no * channels connected, unless it is looping * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) { ppp_recv_unlock(ppp); break; } ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; schedule(); } set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); if (!skb) goto out; ret = -EOVERFLOW; if (skb->len > count) goto outf; ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; iov_iter_init(&to, ITER_DEST, &iov, 1, count); if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; outf: kfree_skb(skb); out: return ret; } static bool ppp_check_packet(struct sk_buff *skb, size_t count) { /* LCP packets must include LCP header which 4 bytes long: * 1-byte code, 1-byte identifier, and 2-byte length. */ return get_unaligned_be16(skb->data) != PPP_LCP || count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; } static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; struct sk_buff *skb; ssize_t ret; if (!pf) return -ENXIO; /* All PPP packets should start with the 2-byte protocol */ if (count < PPP_PROTO_LEN) return -EINVAL; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); goto out; } ret = -EINVAL; if (unlikely(!ppp_check_packet(skb, count))) { kfree_skb(skb); goto out; } switch (pf->kind) { case INTERFACE: ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } ret = count; out: return ret; } /* No kernel lock - fine */ static __poll_t ppp_poll(struct file *file, poll_table *wait) { struct ppp_file *pf = file->private_data; __poll_t mask; if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } return mask; } #ifdef CONFIG_PPP_FILTER static struct bpf_prog *get_filter(struct sock_fprog *uprog) { struct sock_fprog_kern fprog; struct bpf_prog *res = NULL; int err; if (!uprog->len) return NULL; /* uprog->len is unsigned short, so no overflow here */ fprog.len = uprog->len; fprog.filter = memdup_array_user(uprog->filter, uprog->len, sizeof(struct sock_filter)); if (IS_ERR(fprog.filter)) return ERR_CAST(fprog.filter); err = bpf_prog_create(&res, &fprog); kfree(fprog.filter); return err ? ERR_PTR(err) : res; } static struct bpf_prog *ppp_get_filter(struct sock_fprog __user *p) { struct sock_fprog uprog; if (copy_from_user(&uprog, p, sizeof(struct sock_fprog))) return ERR_PTR(-EFAULT); return get_filter(&uprog); } #ifdef CONFIG_COMPAT struct sock_fprog32 { unsigned short len; compat_caddr_t filter; }; #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) { struct sock_fprog32 uprog32; struct sock_fprog uprog; if (copy_from_user(&uprog32, p, sizeof(struct sock_fprog32))) return ERR_PTR(-EFAULT); uprog.len = uprog32.len; uprog.filter = compat_ptr(uprog32.filter); return get_filter(&uprog); } #endif #endif /* Bridge one PPP channel to another. * When two channels are bridged, ppp_input on one channel is redirected to * the other's ops->start_xmit handler. * In order to safely bridge channels we must reject channels which are already * part of a bridge instance, or which form part of an existing unit. * Once successfully bridged, each channel holds a reference on the other * to prevent it being freed while the bridge is extant. */ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) { write_lock_bh(&pch->upl); if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { write_unlock_bh(&pch->upl); return -EALREADY; } refcount_inc(&pchb->file.refcnt); rcu_assign_pointer(pch->bridge, pchb); write_unlock_bh(&pch->upl); write_lock_bh(&pchb->upl); if (pchb->ppp || rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { write_unlock_bh(&pchb->upl); goto err_unset; } refcount_inc(&pch->file.refcnt); rcu_assign_pointer(pchb->bridge, pch); write_unlock_bh(&pchb->upl); return 0; err_unset: write_lock_bh(&pch->upl); /* Re-read pch->bridge with upl held in case it was modified concurrently */ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); synchronize_rcu(); if (pchb) if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return -EALREADY; } static int ppp_unbridge_channels(struct channel *pch) { struct channel *pchb, *pchbb; write_lock_bh(&pch->upl); pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); if (!pchb) { write_unlock_bh(&pch->upl); return -EINVAL; } RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); /* Only modify pchb if phcb->bridge points back to pch. * If not, it implies that there has been a race unbridging (and possibly * even rebridging) pchb. We should leave pchb alone to avoid either a * refcount underflow, or breaking another established bridge instance. */ write_lock_bh(&pchb->upl); pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); if (pchbb == pch) RCU_INIT_POINTER(pchb->bridge, NULL); write_unlock_bh(&pchb->upl); synchronize_rcu(); if (pchbb == pch) if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return 0; } static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle32 idle32; struct ppp_idle64 idle64; struct npioctl npi; int unit, cflags; struct slcompress *vj; void __user *argp = (void __user *)arg; int __user *p = argp; mutex_lock(&ppp_mutex); pf = file->private_data; if (!pf) { err = ppp_unattached_ioctl(current->nsproxy->net_ns, pf, file, cmd, arg); goto out; } if (cmd == PPPIOCDETACH) { /* * PPPIOCDETACH is no longer supported as it was heavily broken, * and is only known to have been used by pppd older than * ppp-2.4.2 (released November 2003). */ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n", current->comm, current->pid); err = -EINVAL; goto out; } if (pf->kind == CHANNEL) { struct channel *pch, *pchb; struct ppp_channel *chan; struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); switch (cmd) { case PPPIOCCONNECT: if (get_user(unit, p)) break; err = ppp_connect_channel(pch, unit); break; case PPPIOCDISCONN: err = ppp_disconnect_channel(pch); break; case PPPIOCBRIDGECHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(current->nsproxy->net_ns); spin_lock_bh(&pn->all_channels_lock); pchb = ppp_find_channel(pn, unit); /* Hold a reference to prevent pchb being freed while * we establish the bridge. */ if (pchb) refcount_inc(&pchb->file.refcnt); spin_unlock_bh(&pn->all_channels_lock); if (!pchb) break; err = ppp_bridge_channels(pch, pchb); /* Drop earlier refcount now bridge establishment is complete */ if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); break; case PPPIOCUNBRIDGECHAN: err = ppp_unbridge_channels(pch); break; default: down_read(&pch->chan_sem); chan = pch->chan; err = -ENOTTY; if (chan && chan->ops->ioctl) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); err = -EINVAL; goto out; } ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: if (get_user(val, p)) break; ppp->mru = val; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ppp_lock(ppp); cflags = ppp->flags & ~val; #ifdef CONFIG_PPP_MULTILINK if (!(ppp->flags & SC_MULTILINK) && (val & SC_MULTILINK)) ppp->nextseq = 0; #endif ppp->flags = val & SC_FLAG_BITS; ppp_unlock(ppp); if (cflags & SC_CCP_OPEN) ppp_ccp_closed(ppp); err = 0; break; case PPPIOCGFLAGS: val = ppp->flags | ppp->xstate | ppp->rstate; if (put_user(val, p)) break; err = 0; break; case PPPIOCSCOMPRESS: { struct ppp_option_data data; if (copy_from_user(&data, argp, sizeof(data))) err = -EFAULT; else err = ppp_set_compress(ppp, &data); break; } case PPPIOCGUNIT: if (put_user(ppp->file.index, p)) break; err = 0; break; case PPPIOCSDEBUG: if (get_user(val, p)) break; ppp->debug = val; err = 0; break; case PPPIOCGDEBUG: if (put_user(ppp->debug, p)) break; err = 0; break; case PPPIOCGIDLE32: idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; break; case PPPIOCSMAXCID: if (get_user(val, p)) break; val2 = 15; if ((val >> 16) != 0) { val2 = val >> 16; val &= 0xffff; } vj = slhc_init(val2+1, val+1); if (IS_ERR(vj)) { err = PTR_ERR(vj); break; } ppp_lock(ppp); if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); err = 0; break; case PPPIOCGNPMODE: case PPPIOCSNPMODE: if (copy_from_user(&npi, argp, sizeof(npi))) break; err = proto_to_npindex(npi.protocol); if (err < 0) break; i = err; if (cmd == PPPIOCGNPMODE) { err = -EFAULT; npi.mode = ppp->npmode[i]; if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { ppp->npmode[i] = npi.mode; /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } err = 0; break; #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS: case PPPIOCSACTIVE: { struct bpf_prog *filter = ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ #ifdef CONFIG_PPP_MULTILINK case PPPIOCSMRRU: if (get_user(val, p)) break; ppp_recv_lock(ppp); ppp->mrru = val; ppp_recv_unlock(ppp); err = 0; break; #endif /* CONFIG_PPP_MULTILINK */ default: err = -ENOTTY; } out: mutex_unlock(&ppp_mutex); return err; } #ifdef CONFIG_COMPAT struct ppp_option_data32 { compat_uptr_t ptr; u32 length; compat_int_t transmit; }; #define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32) static long ppp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; int err = -ENOIOCTLCMD; void __user *argp = (void __user *)arg; mutex_lock(&ppp_mutex); pf = file->private_data; if (pf && pf->kind == INTERFACE) { struct ppp *ppp = PF_TO_PPP(pf); switch (cmd) { #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS32: case PPPIOCSACTIVE32: { struct bpf_prog *filter = compat_ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS32) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ case PPPIOCSCOMPRESS32: { struct ppp_option_data32 data32; if (copy_from_user(&data32, argp, sizeof(data32))) { err = -EFAULT; } else { struct ppp_option_data data = { .ptr = compat_ptr(data32.ptr), .length = data32.length, .transmit = data32.transmit }; err = ppp_set_compress(ppp, &data); } break; } } } mutex_unlock(&ppp_mutex); /* all other commands have compatible arguments */ if (err == -ENOIOCTLCMD) err = ppp_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); return err; } #endif static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg) { int unit, err = -EFAULT; struct ppp *ppp; struct channel *chan; struct ppp_net *pn; int __user *p = (int __user *)arg; switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ if (get_user(unit, p)) break; err = ppp_create_interface(net, file, &unit); if (err < 0) break; err = -EFAULT; if (put_user(unit, p)) break; err = 0; break; case PPPIOCATTACH: /* Attach to an existing ppp unit */ if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (ppp) { refcount_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; } mutex_unlock(&pn->all_ppp_mutex); break; case PPPIOCATTCHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); spin_lock_bh(&pn->all_channels_lock); chan = ppp_find_channel(pn, unit); if (chan) { refcount_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; } spin_unlock_bh(&pn->all_channels_lock); break; default: err = -ENOTTY; } return err; } static const struct file_operations ppp_device_fops = { .owner = THIS_MODULE, .read = ppp_read, .write = ppp_write, .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ppp_compat_ioctl, #endif .open = ppp_open, .release = ppp_release, .llseek = noop_llseek, }; static void ppp_nl_dellink(struct net_device *dev, struct list_head *head); static __net_init int ppp_init_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); INIT_LIST_HEAD(&pn->all_channels); INIT_LIST_HEAD(&pn->new_channels); spin_lock_init(&pn->all_channels_lock); return 0; } static __net_exit void ppp_exit_rtnl_net(struct net *net, struct list_head *dev_to_kill) { struct ppp_net *pn = net_generic(net, ppp_net_id); struct ppp *ppp; int id; idr_for_each_entry(&pn->units_idr, ppp, id) ppp_nl_dellink(ppp->dev, dev_to_kill); } static __net_exit void ppp_exit_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); mutex_destroy(&pn->all_ppp_mutex); idr_destroy(&pn->units_idr); WARN_ON_ONCE(!list_empty(&pn->all_channels)); WARN_ON_ONCE(!list_empty(&pn->new_channels)); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit_rtnl = ppp_exit_rtnl_net, .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) { struct ppp_net *pn = ppp_pernet(ppp->ppp_net); int ret; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); if (ret < 0) goto err; } } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST * too if idr allocation fails; this makes pppd retry without * requesting a specific unit number. */ if (unit_find(&pn->units_idr, unit)) { ret = -EEXIST; goto err; } ret = unit_set(&pn->units_idr, ppp, unit); if (ret < 0) { /* Rewrite error for backward compatibility */ ret = -EEXIST; goto err; } } ppp->file.index = ret; if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); return 0; err_unit: mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); return ret; } static int ppp_dev_configure(struct net *src_net, struct net_device *dev, const struct ppp_config *conf) { struct ppp *ppp = netdev_priv(dev); int indx; int err; int cpu; ppp->dev = dev; ppp->ppp_net = src_net; ppp->mru = PPP_MRU; ppp->owner = conf->file; init_ppp_file(&ppp->file, INTERFACE); ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */ for (indx = 0; indx < NUM_NP; ++indx) ppp->npmode[indx] = NPMODE_PASS; INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); ppp->xmit_recursion = alloc_percpu(int); if (!ppp->xmit_recursion) { err = -ENOMEM; goto err1; } for_each_possible_cpu(cpu) (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER ppp->pass_filter = NULL; ppp->active_filter = NULL; #endif /* CONFIG_PPP_FILTER */ err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) goto err2; conf->file->private_data = &ppp->file; return 0; err2: free_percpu(ppp->xmit_recursion); err1: return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; if (!data[IFLA_PPP_DEV_FD]) return -EINVAL; if (nla_get_s32(data[IFLA_PPP_DEV_FD]) < 0) return -EBADF; return 0; } static int ppp_nl_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ppp_config conf = { .unit = -1, .ifname_is_set = true, }; struct file *file; int err; file = fget(nla_get_s32(data[IFLA_PPP_DEV_FD])); if (!file) return -EBADF; /* rtnl_lock is already held here, but ppp_create_interface() locks * ppp_mutex before holding rtnl_lock. Using mutex_trylock() avoids * possible deadlock due to lock order inversion, at the cost of * pushing the problem back to userspace. */ if (!mutex_trylock(&ppp_mutex)) { err = -EBUSY; goto out; } if (file->f_op != &ppp_device_fops || file->private_data) { err = -EBADF; goto out_unlock; } conf.file = file; /* Don't use device name generated by the rtnetlink layer when ifname * isn't specified. Let ppp_dev_configure() set the device name using * the PPP unit identifer as suffix (i.e. ppp<unit_id>). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(link_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); out: fput(file); return err; } static void ppp_nl_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static size_t ppp_nl_get_size(const struct net_device *dev) { return 0; } static int ppp_nl_fill_info(struct sk_buff *skb, const struct net_device *dev) { return 0; } static struct net *ppp_nl_get_link_net(const struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); return READ_ONCE(ppp->ppp_net); } static struct rtnl_link_ops ppp_link_ops __read_mostly = { .kind = "ppp", .maxtype = IFLA_PPP_MAX, .policy = ppp_nl_policy, .priv_size = sizeof(struct ppp), .setup = ppp_setup, .validate = ppp_nl_validate, .newlink = ppp_nl_newlink, .dellink = ppp_nl_dellink, .get_size = ppp_nl_get_size, .fill_info = ppp_nl_fill_info, .get_link_net = ppp_nl_get_link_net, }; #define PPP_MAJOR 108 /* Called at boot time if ppp is compiled into the kernel, or at module load time (from init_module) if compiled as a module. */ static int __init ppp_init(void) { int err; pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { pr_err("failed to register PPP device (%d)\n", err); goto out_net; } err = class_register(&ppp_class); if (err) goto out_chrdev; err = rtnl_link_register(&ppp_link_ops); if (err) { pr_err("failed to register rtnetlink PPP handler\n"); goto out_class; } /* not a big deal if we fail here :-) */ device_create(&ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: class_unregister(&ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: unregister_pernet_device(&ppp_net_ops); out: return err; } /* * Network interface unit routines. */ static netdev_tx_t ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); int npi, proto; unsigned char *pp; npi = ethertype_to_npindex(ntohs(skb->protocol)); if (npi < 0) goto outf; /* Drop, accept or reject the packet */ switch (ppp->npmode[npi]) { case NPMODE_PASS: break; case NPMODE_QUEUE: /* it would be nice to have a way to tell the network system to queue this one up for later. */ goto outf; case NPMODE_DROP: case NPMODE_ERROR: goto outf; } /* Put the 2-byte PPP protocol number on the front, making sure there is room for the address and control fields. */ if (skb_cow_head(skb, PPP_HDRLEN)) goto outf; pp = skb_push(skb, 2); proto = npindex_to_proto[npi]; put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); ppp_xmit_process(ppp, skb); return NETDEV_TX_OK; outf: kfree_skb(skb); ++dev->stats.tx_dropped; return NETDEV_TX_OK; } static int ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *addr, int cmd) { struct ppp *ppp = netdev_priv(dev); int err = -EFAULT; struct ppp_stats stats; struct ppp_comp_stats cstats; char *vers; switch (cmd) { case SIOCGPPPSTATS: ppp_get_stats(ppp, &stats); if (copy_to_user(addr, &stats, sizeof(stats))) break; err = 0; break; case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; err = 0; break; case SIOCGPPPVER: vers = PPP_VERSION; if (copy_to_user(addr, vers, strlen(vers) + 1)) break; err = 0; break; default: err = -EINVAL; } return err; } static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { stats64->rx_errors = dev->stats.rx_errors; stats64->tx_errors = dev->stats.tx_errors; stats64->rx_dropped = dev->stats.rx_dropped; stats64->tx_dropped = dev->stats.tx_dropped; stats64->rx_length_errors = dev->stats.rx_length_errors; dev_fetch_sw_netstats(stats64, dev->tstats); } static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; netdev_lockdep_set_classes(dev); ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets * unregistered. */ refcount_inc(&ppp->file.refcnt); return 0; } static void ppp_dev_uninit(struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); struct ppp_net *pn = ppp_pernet(ppp->ppp_net); ppp_lock(ppp); ppp->closing = 1; ppp_unlock(ppp); mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ppp->owner = NULL; ppp->file.dead = 1; wake_up_interruptible(&ppp->file.rwait); } static void ppp_dev_priv_destructor(struct net_device *dev) { struct ppp *ppp; ppp = netdev_priv(dev); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); } static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ppp *ppp = netdev_priv(ctx->dev); struct ppp_channel *chan; struct channel *pch; if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; if (list_empty(&ppp->channels)) return -ENODEV; pch = list_first_entry(&ppp->channels, struct channel, clist); chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; return chan->ops->fill_forward_path(ctx, path, chan); } static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, .ndo_start_xmit = ppp_start_xmit, .ndo_siocdevprivate = ppp_net_siocdevprivate, .ndo_get_stats64 = ppp_get_stats64, .ndo_fill_forward_path = ppp_fill_forward_path, }; static const struct device_type ppp_type = { .name = "ppp", }; static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); dev->lltx = true; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->priv_destructor = ppp_dev_priv_destructor; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); } /* * Transmit-side routines. */ /* Called to do any work queued up on the transmit side that can now be done */ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); if (skb) skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); } else { kfree_skb(skb); } ppp_xmit_unlock(ppp); } static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); return; err: local_bh_enable(); kfree_skb(skb); if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } static inline struct sk_buff * pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *new_skb; int len; int new_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + ppp->dev->hard_header_len; int compressor_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + PPP_HDRLEN; new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) skb_reserve(new_skb, ppp->dev->hard_header_len - PPP_HDRLEN); /* compressor still expects A/C bytes in hdr */ len = ppp->xcomp->compress(ppp->xc_state, skb->data - 2, new_skb->data, skb->len + 2, compressor_skb_size); if (len > 0 && (ppp->flags & SC_CCP_UP)) { consume_skb(skb); skb = new_skb; skb_put(skb, len); skb_pull(skb, 2); /* pull off A/C bytes */ } else if (len == 0) { /* didn't compress, or CCP not up yet */ consume_skb(new_skb); new_skb = skb; } else { /* * (len < 0) * MPPE requires that we do not send unencrypted * frames. The compressor will return -1 if we * should drop the frame. We cannot simply test * the compress_proto because MPPE and MPPC share * the same number. */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } return new_skb; } /* * Compress and send a frame. * The caller should have locked the xmit path, * and xmit_pending should be 0. */ static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *new_skb; int len; unsigned char *cp; skb->dev = ppp->dev; if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if the packet passes the pass and active filters. * See comment for PPP_FILTER_OUTBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else /* for data packets, record the time */ ppp->last_xmit = jiffies; #endif /* CONFIG_PPP_FILTER */ } dev_sw_netstats_tx_add(ppp->dev, 1, skb->len - PPP_PROTO_LEN); switch (proto) { case PPP_IP: if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); cp = skb->data + 2; len = slhc_compress(ppp->vj, cp, skb->len - 2, new_skb->data + 2, &cp, !(ppp->flags & SC_NO_TCP_CCID)); if (cp == skb->data + 2) { /* didn't compress */ consume_skb(new_skb); } else { if (cp[0] & SL_TYPE_COMPRESSED_TCP) { proto = PPP_VJC_COMP; cp[0] &= ~SL_TYPE_COMPRESSED_TCP; } else { proto = PPP_VJC_UNCOMP; cp[0] = skb->data[2]; } consume_skb(skb); skb = new_skb; cp = skb_put(skb, len + 2); cp[0] = 0; cp[1] = proto; } break; case PPP_CCP: /* peek at outbound CCP frames */ ppp_ccp_peek(ppp, skb, 0); break; } /* try to do packet compression */ if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compression required but " "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); if (!skb) goto drop; } /* * If we are waiting for traffic (demand dialling), * queue it up for pppd to receive. */ if (ppp->flags & SC_LOOP_TRAFFIC) { if (ppp->file.rq.qlen > PPP_MAX_RQLEN) goto drop; skb_queue_tail(&ppp->file.rq, skb); wake_up_interruptible(&ppp->file.rwait); return; } ppp->xmit_pending = skb; ppp_push(ppp); return; drop: kfree_skb(skb); ++ppp->dev->stats.tx_errors; } /* * Try to send the frame in xmit_pending. * The caller should have the xmit path locked. */ static void ppp_push(struct ppp *ppp) { struct list_head *list; struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; if (!skb) return; list = &ppp->channels; if (list_empty(list)) { /* nowhere to send the packet, just drop it */ ppp->xmit_pending = NULL; kfree_skb(skb); return; } if ((ppp->flags & SC_MULTILINK) == 0) { /* not doing multilink: send it down the first channel */ list = list->next; pch = list_entry(list, struct channel, clist); spin_lock(&pch->downl); if (pch->chan) { if (pch->chan->ops->start_xmit(pch->chan, skb)) ppp->xmit_pending = NULL; } else { /* channel got unregistered */ kfree_skb(skb); ppp->xmit_pending = NULL; } spin_unlock(&pch->downl); return; } #ifdef CONFIG_PPP_MULTILINK /* Multilink: fragment the packet over as many links as can take the packet at the moment. */ if (!ppp_mp_explode(ppp, skb)) return; #endif /* CONFIG_PPP_MULTILINK */ ppp->xmit_pending = NULL; kfree_skb(skb); } #ifdef CONFIG_PPP_MULTILINK static bool mp_protocol_compress __read_mostly = true; module_param(mp_protocol_compress, bool, 0644); MODULE_PARM_DESC(mp_protocol_compress, "compress protocol id in multilink fragments"); /* * Divide a packet to be transmitted into fragments and * send them out the individual links. */ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) { int len, totlen; int i, bits, hdrlen, mtu; int flen; int navail, nfree, nzero; int nbigger; int totspeed; int totfree; unsigned char *p, *q; struct list_head *list; struct channel *pch; struct sk_buff *frag; struct ppp_channel *chan; totspeed = 0; /*total bitrate of the bundle*/ nfree = 0; /* # channels which have no packet already queued */ navail = 0; /* total # of usable channels (not deregistered) */ nzero = 0; /* number of channels with zero speed associated*/ totfree = 0; /*total # of channels available and *having no queued packets before *starting the fragmentation*/ hdrlen = (ppp->flags & SC_MP_XSHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; i = 0; list_for_each_entry(pch, &ppp->channels, clist) { if (pch->chan) { pch->avail = 1; navail++; pch->speed = pch->chan->speed; } else { pch->avail = 0; } if (pch->avail) { if (skb_queue_empty(&pch->file.xq) || !pch->had_frag) { if (pch->speed == 0) nzero++; else totspeed += pch->speed; pch->avail = 2; ++nfree; ++totfree; } if (!pch->had_frag && i < ppp->nxchan) ppp->nxchan = i; } ++i; } /* * Don't start sending this packet unless at least half of * the channels are free. This gives much better TCP * performance if we have a lot of channels. */ if (nfree == 0 || nfree < navail / 2) return 0; /* can't take now, leave it in xmit_pending */ /* Do protocol field compression */ p = skb->data; len = skb->len; if (*p == 0 && mp_protocol_compress) { ++p; --len; } totlen = len; nbigger = len % nfree; /* skip to the channel after the one we last used and start at that one */ list = &ppp->channels; for (i = 0; i < ppp->nxchan; ++i) { list = list->next; if (list == &ppp->channels) { i = 0; break; } } /* create a fragment for each channel */ bits = B; while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; continue; } pch = list_entry(list, struct channel, clist); ++i; if (!pch->avail) continue; /* * Skip this channel if it has a fragment pending already and * we haven't given a fragment to all of the free channels. */ if (pch->avail == 1) { if (nfree > 0) continue; } else { pch->avail = 1; } /* check the channel's mtu and whether it is still attached. */ spin_lock(&pch->downl); if (pch->chan == NULL) { /* can't use this channel, it's being deregistered */ if (pch->speed == 0) nzero--; else totspeed -= pch->speed; spin_unlock(&pch->downl); pch->avail = 0; totlen = len; totfree--; nfree--; if (--navail == 0) break; continue; } /* *if the channel speed is not set divide *the packet evenly among the free channels; *otherwise divide it according to the speed *of the channel we are going to transmit on */ flen = len; if (nfree > 0) { if (pch->speed == 0) { flen = len/nfree; if (nbigger > 0) { flen++; nbigger--; } } else { flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / ((totspeed*totfree)/pch->speed)) - hdrlen; if (nbigger > 0) { flen += ((totfree - nzero)*pch->speed)/totspeed; nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; } } nfree--; } /* *check if we are on the last channel or *we exceded the length of the data to *fragment */ if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: *in that case from the resulting flen according to the *above formula will be equal or less than zero. *Skip the channel in this case */ if (flen <= 0) { pch->avail = 2; spin_unlock(&pch->downl); continue; } /* * hdrlen includes the 2-byte PPP protocol field, but the * MTU counts only the payload excluding the protocol field. * (RFC1661 Section 2) */ mtu = pch->chan->mtu - (hdrlen - 2); if (mtu < 4) mtu = 4; if (flen > mtu) flen = mtu; if (flen == len) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); /* make the MP header */ put_unaligned_be16(PPP_MP, q); if (ppp->flags & SC_MP_XSHORTSEQ) { q[2] = bits + ((ppp->nxseq >> 8) & 0xf); q[3] = ppp->nxseq; } else { q[2] = bits; q[3] = ppp->nxseq >> 16; q[4] = ppp->nxseq >> 8; q[5] = ppp->nxseq; } memcpy(q + hdrlen, p, flen); /* try to send it down the channel */ chan = pch->chan; if (!skb_queue_empty(&pch->file.xq) || !chan->ops->start_xmit(chan, frag)) skb_queue_tail(&pch->file.xq, frag); pch->had_frag = 1; p += flen; len -= flen; ++ppp->nxseq; bits = 0; spin_unlock(&pch->downl); } ppp->nxchan = i; return 1; noskb: spin_unlock(&pch->downl); if (ppp->debug & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ } #endif /* CONFIG_PPP_MULTILINK */ /* Try to send data out on a channel */ static void __ppp_channel_push(struct channel *pch) { struct sk_buff *skb; struct ppp *ppp; spin_lock(&pch->downl); if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { /* put the packet back and try again later */ skb_queue_head(&pch->file.xq, skb); break; } } } else { /* channel got deregistered */ skb_queue_purge(&pch->file.xq); } spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) __ppp_xmit_process(ppp, NULL); } } static void ppp_channel_push(struct channel *pch) { read_lock_bh(&pch->upl); if (pch->ppp) { (*this_cpu_ptr(pch->ppp->xmit_recursion))++; __ppp_channel_push(pch); (*this_cpu_ptr(pch->ppp->xmit_recursion))--; } else { __ppp_channel_push(pch); } read_unlock_bh(&pch->upl); } /* * Receive-side routines. */ struct ppp_mp_skb_parm { u32 sequence; u8 BEbits; }; #define PPP_MP_CB(skb) ((struct ppp_mp_skb_parm *)((skb)->cb)) static inline void ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); if (!ppp->closing) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); ppp_recv_unlock(ppp); } /** * __ppp_decompress_proto - Decompress protocol field, slim version. * @skb: Socket buffer where protocol field should be decompressed. It must have * at least 1 byte of head room and 1 byte of linear data. First byte of * data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data * length are done in this function. */ static void __ppp_decompress_proto(struct sk_buff *skb) { if (skb->data[0] & 0x01) *(u8 *)skb_push(skb, 1) = 0x00; } /** * ppp_decompress_proto - Check skb data room and decompress protocol field. * @skb: Socket buffer where protocol field should be decompressed. First byte * of data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. This function also makes * sure that skb data room is sufficient for Protocol field, before and after * decompression. * * Return: true - decompressed successfully, false - not enough room in skb. */ static bool ppp_decompress_proto(struct sk_buff *skb) { /* At least one byte should be present (if protocol is compressed) */ if (!pskb_may_pull(skb, 1)) return false; __ppp_decompress_proto(skb); /* Protocol field should occupy 2 bytes when not compressed */ return pskb_may_pull(skb, 2); } /* Attempt to handle a frame via. a bridged channel, if one exists. * If the channel is bridged, the frame is consumed by the bridge. * If not, the caller must handle the frame by normal recv mechanisms. * Returns true if the frame is consumed, false otherwise. */ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) { struct channel *pchb; rcu_read_lock(); pchb = rcu_dereference(pch->bridge); if (!pchb) goto out_rcu; spin_lock_bh(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); goto outl; } skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) kfree_skb(skb); outl: spin_unlock_bh(&pchb->downl); out_rcu: rcu_read_unlock(); /* If pchb is set then we've consumed the packet */ return !!pchb; } void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { struct channel *pch = chan->ppp; int proto; if (!pch) { kfree_skb(skb); return; } /* If the channel is bridged, transmit via. bridge */ if (ppp_channel_bridge_input(pch, skb)) return; read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; ppp_receive_error(pch->ppp); } goto done; } proto = PPP_PROTO(skb); if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { ppp_do_recv(pch->ppp, skb, pch); } done: read_unlock_bh(&pch->upl); } /* Put a 0-length skb in the receive queue as an error indication */ void ppp_input_error(struct ppp_channel *chan, int code) { struct channel *pch = chan->ppp; struct sk_buff *skb; if (!pch) return; read_lock_bh(&pch->upl); if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); } } read_unlock_bh(&pch->upl); } /* * We come in here to process a received frame. * The receive side of the ppp unit is locked. */ static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { /* note: a 0-length skb is used as an error indication */ if (skb->len > 0) { skb_checksum_complete_unset(skb); #ifdef CONFIG_PPP_MULTILINK /* XXX do channel-level decompression here */ if (PPP_PROTO(skb) == PPP_MP) ppp_receive_mp_frame(ppp, skb, pch); else #endif /* CONFIG_PPP_MULTILINK */ ppp_receive_nonmp_frame(ppp, skb); } else { kfree_skb(skb); ppp_receive_error(ppp); } } static void ppp_receive_error(struct ppp *ppp) { ++ppp->dev->stats.rx_errors; if (ppp->vj) slhc_toss(ppp->vj); } static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *ns; int proto, len, npi; /* * Decompress the frame, if compressed. * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; /* At this point the "Protocol" field MUST be decompressed, either in * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { netdev_err(ppp->dev, "PPP: no memory " "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len); consume_skb(skb); skb = ns; } else skb->ip_summed = CHECKSUM_NONE; len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { netdev_printk(KERN_DEBUG, ppp->dev, "PPP: VJ decompression error\n"); goto err; } len += 2; if (len > skb->len) skb_put(skb, len - skb->len); else if (len < skb->len) skb_trim(skb, len); proto = PPP_IP; break; case PPP_VJC_UNCOMP: if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; break; case PPP_CCP: ppp_ccp_peek(ppp, skb, 1); break; } dev_sw_netstats_rx_add(ppp->dev, skb->len - PPP_PROTO_LEN); npi = proto_to_npindex(proto); if (npi < 0) { /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); } else { /* network protocol frame - give it to the kernel */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter || ppp->active_filter) { if (skb_unclone(skb, GFP_ATOMIC)) goto err; /* Check if the packet passes the pass and active filters. * See comment for PPP_FILTER_INBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; if ((ppp->dev->flags & IFF_UP) == 0 || ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ skb_pull_rcsum(skb, 2); skb->dev = ppp->dev; skb->protocol = htons(npindex_to_ethertype[npi]); skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(ppp->dev))); netif_rx(skb); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } static struct sk_buff * ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *ns; int len; /* Until we fix all the decompressor's need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (proto == PPP_COMP) { int obuff_size; switch(ppp->rcomp->compress_proto) { case CI_MPPE: obuff_size = ppp->mru + PPP_HDRLEN + 1; break; default: obuff_size = ppp->mru + PPP_HDRLEN; break; } ns = dev_alloc_skb(obuff_size); if (!ns) { netdev_err(ppp->dev, "ppp_decompress_frame: " "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ len = ppp->rcomp->decompress(ppp->rc_state, skb->data - 2, skb->len + 2, ns->data, obuff_size); if (len < 0) { /* Pass the compressed frame to pppd as an error indication. */ if (len == DECOMP_FATALERROR) ppp->rstate |= SC_DC_FERROR; kfree_skb(ns); goto err; } consume_skb(skb); skb = ns; skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ /* Don't call __ppp_decompress_proto() here, but instead rely on * corresponding algo (mppe/bsd/deflate) to decompress it. */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ if (ppp->rcomp->incomp) ppp->rcomp->incomp(ppp->rc_state, skb->data - 2, skb->len + 2); } return skb; err: ppp->rstate |= SC_DC_ERROR; ppp_receive_error(ppp); return skb; } #ifdef CONFIG_PPP_MULTILINK /* * Receive a multilink frame. * We put it on the reconstruction queue and then pull off * as many completed frames as we can. */ static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { u32 mask, seq; struct channel *ch; int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0) goto err; /* no good, throw it away */ /* Decode sequence number and begin/end bits */ if (ppp->flags & SC_MP_SHORTSEQ) { seq = ((skb->data[2] & 0x0f) << 8) | skb->data[3]; mask = 0xfff; } else { seq = (skb->data[3] << 16) | (skb->data[4] << 8)| skb->data[5]; mask = 0xffffff; } PPP_MP_CB(skb)->BEbits = skb->data[2]; skb_pull(skb, mphdrlen); /* pull off PPP and MP headers */ /* * Do protocol ID decompression on the first fragment of each packet. * We have to do that here, because ppp_receive_nonmp_frame() expects * decompressed protocol field. */ if (PPP_MP_CB(skb)->BEbits & B) __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close * as possible to ppp->minseq. */ seq |= ppp->minseq & ~mask; if ((int)(ppp->minseq - seq) > (int)(mask >> 1)) seq += mask + 1; else if ((int)(seq - ppp->minseq) > (int)(mask >> 1)) seq -= mask + 1; /* should never happen */ PPP_MP_CB(skb)->sequence = seq; pch->lastseq = seq; /* * If this packet comes before the next one we were expecting, * drop it. */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); return; } /* * Reevaluate minseq, the minimum over all channels of the * last sequence number received on each channel. Because of * the increasing sequence number rule, we know that any fragment * before `minseq' which hasn't arrived is never going to arrive. * The list of channels can't change because we have the receive * side of the ppp unit locked. */ list_for_each_entry(ch, &ppp->channels, clist) { if (seq_before(ch->lastseq, seq)) seq = ch->lastseq; } if (seq_before(ppp->minseq, seq)) ppp->minseq = seq; /* Put the fragment on the reconstruction queue */ ppp_mp_insert(ppp, skb); /* If the queue is getting long, don't wait any longer for packets before the start of the queue. */ if (skb_queue_len(&ppp->mrq) >= PPP_MP_MAX_QLEN) { struct sk_buff *mskb = skb_peek(&ppp->mrq); if (seq_before(ppp->minseq, PPP_MP_CB(mskb)->sequence)) ppp->minseq = PPP_MP_CB(mskb)->sequence; } /* Pull completed packets off the queue and receive them. */ while ((skb = ppp_mp_reconstruct(ppp))) { if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { ++ppp->dev->stats.rx_length_errors; kfree_skb(skb); ppp_receive_error(ppp); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } /* * Insert a fragment on the MP reconstruction queue. * The queue is ordered by increasing sequence number. */ static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *p; struct sk_buff_head *list = &ppp->mrq; u32 seq = PPP_MP_CB(skb)->sequence; /* N.B. we don't need to lock the list lock because we have the ppp unit receive-side lock. */ skb_queue_walk(list, p) { if (seq_before(seq, PPP_MP_CB(p)->sequence)) break; } __skb_queue_before(list, p, skb); } /* * Reconstruct a packet from the MP fragment queue. * We go through increasing sequence numbers until we find a * complete packet, or we get to the sequence number for a fragment * which hasn't arrived but might still do so. */ static struct sk_buff * ppp_mp_reconstruct(struct ppp *ppp) { u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ netdev_err(ppp->dev, "ppp_mp_reconstruct bad " "seq %u < %u\n", PPP_MP_CB(p)->sequence, seq); __skb_unlink(p, list); kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { u32 oldseq; /* Fragment `seq' is missing. If it is after minseq, it might arrive later, so stop here. */ if (seq_after(seq, minseq)) break; /* Fragment `seq' is lost, keep going. */ lost = 1; oldseq = seq; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); goto again; } /* * At this point we know that all the fragments from * ppp->nextseq to seq are either present or lost. * Also, there are no complete packets in the queue * that have no missing fragments and end before this * fragment. */ /* B bit set indicates this fragment starts a packet */ if (PPP_MP_CB(p)->BEbits & B) { head = p; lost = 0; len = 0; } len += p->len; /* Got a complete packet yet? */ if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); } else { tail = p; break; } ppp->nextseq = seq + 1; } /* * If this is the ending fragment of a packet, * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ if (PPP_MP_CB(p)->BEbits & E) { struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } head = skb_peek(list); if (!head) break; } ++seq; } /* If we have a complete packet, copy it all into one skb. */ if (tail != NULL) { /* If we have discarded any fragments, signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { skb_queue_walk_safe(list, p, tmp) { if (p == head) break; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } skb = head; if (head != tail) { struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; p = skb_queue_next(list, head); __skb_unlink(skb, list); skb_queue_walk_from_safe(list, p, tmp) { __skb_unlink(p, list); *fragpp = p; p->next = NULL; fragpp = &p->next; skb->len += p->len; skb->data_len += p->len; skb->truesize += p->truesize; if (p == tail) break; } } else { __skb_unlink(skb, list); } ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; } #endif /* CONFIG_PPP_MULTILINK */ /* * Channel interface. */ /* Create a new, unattached ppp channel. */ int ppp_register_channel(struct ppp_channel *chan) { return ppp_register_net_channel(current->nsproxy->net_ns, chan); } /* Create a new, unattached ppp channel for specified net. */ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) { struct channel *pch; struct ppp_net *pn; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); if (!pch) return -ENOMEM; pn = ppp_pernet(net); pch->ppp = NULL; pch->chan = chan; pch->chan_net = get_net_track(net, &pch->ns_tracker, GFP_KERNEL); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; #ifdef CONFIG_PPP_MULTILINK pch->lastseq = -1; #endif /* CONFIG_PPP_MULTILINK */ init_rwsem(&pch->chan_sem); spin_lock_init(&pch->downl); rwlock_init(&pch->upl); spin_lock_bh(&pn->all_channels_lock); pch->file.index = ++pn->last_channel_index; list_add(&pch->list, &pn->new_channels); atomic_inc(&channel_count); spin_unlock_bh(&pn->all_channels_lock); return 0; } /* * Return the index of a channel. */ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (pch) return pch->file.index; return -1; } /* * Return the PPP unit number to which a channel is connected. */ int ppp_unit_number(struct ppp_channel *chan) { struct channel *pch = chan->ppp; int unit = -1; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } return unit; } /* * Return the PPP device interface name of a channel. */ char *ppp_dev_name(struct ppp_channel *chan) { struct channel *pch = chan->ppp; char *name = NULL; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp && pch->ppp->dev) name = pch->ppp->dev->name; read_unlock_bh(&pch->upl); } return name; } /* * Disconnect a channel from the generic layer. * This must be called in process context. */ void ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; struct ppp_net *pn; if (!pch) return; /* should never happen */ chan->ppp = NULL; /* * This ensures that we have returned from any calls into * the channel's start_xmit or ioctl routine before we proceed. */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); pch->chan = NULL; spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); pn = ppp_pernet(pch->chan_net); spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); ppp_unbridge_channels(pch); pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } /* * Callback from a channel when it can accept more to transmit. * This should be called at BH/softirq level, not interrupt level. */ void ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (!pch) return; ppp_channel_push(pch); } /* * Compression control. */ /* Process the PPPIOCSCOMPRESS ioctl. */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data) { int err = -EFAULT; struct compressor *cp, *ocomp; void *state, *ostate; unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; if (data->length > CCP_MAX_OPTION_LENGTH) goto out; if (copy_from_user(ccp_option, data->ptr, data->length)) goto out; err = -EINVAL; if (data->length < 2 || ccp_option[1] < 2 || ccp_option[1] > data->length) goto out; cp = try_then_request_module( find_compressor(ccp_option[0]), "ppp-compress-%d", ccp_option[0]); if (!cp) goto out; err = -ENOBUFS; if (data->transmit) { state = cp->comp_alloc(ccp_option, data->length); if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; ostate = ppp->xc_state; ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } else { state = cp->decomp_alloc(ccp_option, data->length); if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; ostate = ppp->rc_state; ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } out: return err; } /* * Look at a CCP packet and update our state accordingly. * We assume the caller has the xmit or recv path locked. */ static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) { unsigned char *dp; int len; if (!pskb_may_pull(skb, CCP_HDRLEN + 2)) return; /* no header */ dp = skb->data + 2; switch (CCP_CODE(dp)) { case CCP_CONFREQ: /* A ConfReq starts negotiation of compression * in one direction of transmission, * and hence brings it down...but which way? * * Remember: * A ConfReq indicates what the sender would like to receive */ if(inbound) /* He is proposing what I should send */ ppp->xstate &= ~SC_COMP_RUN; else /* I am proposing to what he should send */ ppp->rstate &= ~SC_DECOMP_RUN; break; case CCP_TERMREQ: case CCP_TERMACK: /* * CCP is going down, both directions of transmission */ ppp->rstate &= ~SC_DECOMP_RUN; ppp->xstate &= ~SC_COMP_RUN; break; case CCP_CONFACK: if ((ppp->flags & (SC_CCP_OPEN | SC_CCP_UP)) != SC_CCP_OPEN) break; len = CCP_LENGTH(dp); if (!pskb_may_pull(skb, len + 2)) return; /* too short */ dp += CCP_HDRLEN; len -= CCP_HDRLEN; if (len < CCP_OPT_MINLEN || len < CCP_OPT_LENGTH(dp)) break; if (inbound) { /* we will start receiving compressed packets */ if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } } else { /* we will soon start sending compressed packets */ if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) ppp->xstate |= SC_COMP_RUN; } break; case CCP_RESETACK: /* reset the [de]compressor */ if ((ppp->flags & SC_CCP_UP) == 0) break; if (inbound) { if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN)) { ppp->rcomp->decomp_reset(ppp->rc_state); ppp->rstate &= ~SC_DC_ERROR; } } else { if (ppp->xc_state && (ppp->xstate & SC_COMP_RUN)) ppp->xcomp->comp_reset(ppp->xc_state); } break; } } /* Free up compression resources. */ static void ppp_ccp_closed(struct ppp *ppp) { void *xstate, *rstate; struct compressor *xcomp, *rcomp; ppp_lock(ppp); ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP); ppp->xstate = 0; xcomp = ppp->xcomp; xstate = ppp->xc_state; ppp->xc_state = NULL; ppp->rstate = 0; rcomp = ppp->rcomp; rstate = ppp->rc_state; ppp->rc_state = NULL; ppp_unlock(ppp); if (xstate) { xcomp->comp_free(xstate); module_put(xcomp->owner); } if (rstate) { rcomp->decomp_free(rstate); module_put(rcomp->owner); } } /* List of compressors. */ static LIST_HEAD(compressor_list); static DEFINE_SPINLOCK(compressor_list_lock); struct compressor_entry { struct list_head list; struct compressor *comp; }; static struct compressor_entry * find_comp_entry(int proto) { struct compressor_entry *ce; list_for_each_entry(ce, &compressor_list, list) { if (ce->comp->compress_proto == proto) return ce; } return NULL; } /* Register a compressor */ int ppp_register_compressor(struct compressor *cp) { struct compressor_entry *ce; int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); if (!ce) goto out; ret = 0; ce->comp = cp; list_add(&ce->list, &compressor_list); out: spin_unlock(&compressor_list_lock); return ret; } /* Unregister a compressor */ void ppp_unregister_compressor(struct compressor *cp) { struct compressor_entry *ce; spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } spin_unlock(&compressor_list_lock); } /* Find a compressor. */ static struct compressor * find_compressor(int type) { struct compressor_entry *ce; struct compressor *cp = NULL; spin_lock(&compressor_list_lock); ce = find_comp_entry(type); if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; } spin_unlock(&compressor_list_lock); return cp; } /* * Miscelleneous stuff. */ static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) { struct slcompress *vj = ppp->vj; int cpu; memset(st, 0, sizeof(*st)); for_each_possible_cpu(cpu) { struct pcpu_sw_netstats *p = per_cpu_ptr(ppp->dev->tstats, cpu); u64 rx_packets, rx_bytes, tx_packets, tx_bytes; rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); st->p.ppp_ipackets += rx_packets; st->p.ppp_ibytes += rx_bytes; st->p.ppp_opackets += tx_packets; st->p.ppp_obytes += tx_bytes; } st->p.ppp_ierrors = ppp->dev->stats.rx_errors; st->p.ppp_oerrors = ppp->dev->stats.tx_errors; if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; st->vj.vjs_searches = vj->sls_o_searches; st->vj.vjs_misses = vj->sls_o_misses; st->vj.vjs_errorin = vj->sls_i_error; st->vj.vjs_tossed = vj->sls_i_tossed; st->vj.vjs_uncompressedin = vj->sls_i_uncompressed; st->vj.vjs_compressedin = vj->sls_i_compressed; } /* * Stuff for handling the lists of ppp units and channels * and for initialization. */ /* * Create a new ppp interface unit. Fails if it can't allocate memory * or if there is already a unit with the requested number. * unit == -1 means allocate a new number. */ static int ppp_create_interface(struct net *net, struct file *file, int *unit) { struct ppp_config conf = { .file = file, .unit = *unit, .ifname_is_set = false, }; struct net_device *dev; struct ppp *ppp; int err; dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) { err = -ENOMEM; goto err; } dev_net_set(dev, net); dev->rtnl_link_ops = &ppp_link_ops; rtnl_lock(); err = ppp_dev_configure(net, dev, &conf); if (err < 0) goto err_dev; ppp = netdev_priv(dev); *unit = ppp->file.index; rtnl_unlock(); return 0; err_dev: rtnl_unlock(); free_netdev(dev); err: return err; } /* * Initialize a ppp_file structure. */ static void init_ppp_file(struct ppp_file *pf, int kind) { pf->kind = kind; skb_queue_head_init(&pf->xq); skb_queue_head_init(&pf->rq); refcount_set(&pf->refcnt, 1); init_waitqueue_head(&pf->rwait); } /* * Free the memory used by a ppp unit. This is only called once * there are no channels connected to the unit and no file structs * that reference the unit. */ static void ppp_destroy_interface(struct ppp *ppp) { atomic_dec(&ppp_unit_count); if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ netdev_err(ppp->dev, "ppp: destroying ppp struct %p " "but dead=%d n_channels=%d !\n", ppp, ppp->file.dead, ppp->n_channels); return; } ppp_ccp_closed(ppp); if (ppp->vj) { slhc_free(ppp->vj); ppp->vj = NULL; } skb_queue_purge(&ppp->file.xq); skb_queue_purge(&ppp->file.rq); #ifdef CONFIG_PPP_MULTILINK skb_queue_purge(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter) { bpf_prog_destroy(ppp->pass_filter); ppp->pass_filter = NULL; } if (ppp->active_filter) { bpf_prog_destroy(ppp->active_filter); ppp->active_filter = NULL; } #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } /* * Locate an existing ppp unit. * The caller should have locked the all_ppp_mutex. */ static struct ppp * ppp_find_unit(struct ppp_net *pn, int unit) { return unit_find(&pn->units_idr, unit); } /* * Locate an existing ppp channel. * The caller should have locked the all_channels_lock. * First we look in the new_channels list, then in the * all_channels list. If found in the new_channels list, * we move it to the all_channels list. This is for speed * when we have a lot of channels in use. */ static struct channel * ppp_find_channel(struct ppp_net *pn, int unit) { struct channel *pch; list_for_each_entry(pch, &pn->new_channels, list) { if (pch->file.index == unit) { list_move(&pch->list, &pn->all_channels); return pch; } } list_for_each_entry(pch, &pn->all_channels, list) { if (pch->file.index == unit) return pch; } return NULL; } /* * Connect a PPP channel to a PPP interface unit. */ static int ppp_connect_channel(struct channel *pch, int unit) { struct ppp *ppp; struct ppp_net *pn; int ret = -ENXIO; int hdrlen; pn = ppp_pernet(pch->chan_net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); spin_lock_bh(&pch->downl); if (!pch->chan) { /* Don't connect unregistered channels */ spin_unlock_bh(&pch->downl); ppp_unlock(ppp); ret = -ENOTCONN; goto outl; } if (pch->chan->direct_xmit) ppp->dev->priv_flags |= IFF_NO_QUEUE; else ppp->dev->priv_flags &= ~IFF_NO_QUEUE; spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; list_add_tail(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); ppp_unlock(ppp); ret = 0; outl: write_unlock_bh(&pch->upl); out: mutex_unlock(&pn->all_ppp_mutex); return ret; } /* * Disconnect a channel from its ppp unit. */ static int ppp_disconnect_channel(struct channel *pch) { struct ppp *ppp; int err = -EINVAL; write_lock_bh(&pch->upl); ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; } return err; } /* * Free up the resources used by a ppp channel. */ static void ppp_destroy_channel(struct channel *pch) { put_net_track(pch->chan_net, &pch->ns_tracker); pch->chan_net = NULL; atomic_dec(&channel_count); if (!pch->file.dead) { /* "can't happen" */ pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); skb_queue_purge(&pch->file.rq); kfree(pch); } static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); } /* * Units handling. Caller must protect concurrent access * by holding all_ppp_mutex */ /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); if (unit == -ENOSPC) unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr, int min) { return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ static void unit_put(struct idr *p, int n) { idr_remove(p, n); } /* get pointer associated with the number */ static void *unit_find(struct idr *p, int n) { return idr_find(p, n); } /* Module/initialization stuff */ module_init(ppp_init); module_exit(ppp_cleanup); EXPORT_SYMBOL(ppp_register_net_channel); EXPORT_SYMBOL(ppp_register_channel); EXPORT_SYMBOL(ppp_unregister_channel); EXPORT_SYMBOL(ppp_channel_index); EXPORT_SYMBOL(ppp_unit_number); EXPORT_SYMBOL(ppp_dev_name); EXPORT_SYMBOL(ppp_input); EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); MODULE_DESCRIPTION("Generic PPP layer driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); MODULE_ALIAS("devname:ppp"); |
| 248 248 1170 123 123 124 123 1 124 124 122 1 1828 1912 1916 1916 4 1170 801 1826 1828 1830 1680 185 1829 619 617 549 82 618 22 35 56 214 213 214 214 1900 35 1710 255 160 227 1914 1401 580 1876 57 1920 1823 114 1821 130 1708 253 1920 1920 1926 1919 1921 21 1896 35 619 153 2605 2604 2597 2677 456 2599 1511 1919 21 8 8 8 8 550 21 21 21 21 21 21 21 114 114 139 139 139 137 139 137 139 139 1 139 139 138 139 139 139 173 35 139 5994 792 5919 17 5999 112 2515 669 4033 3786 304 5995 5998 5995 1095 5931 5925 9 5793 654 5935 4272 2352 5896 671 5936 852 2340 649 3630 4944 1555 5902 5818 5825 5809 5814 5814 5816 5776 5812 140 140 100 8 8 2 2703 8 2706 441 6 907 2463 2461 56 2446 2510 2514 2519 400 162 2513 4 4 2479 2485 2483 2408 2403 2403 2408 2427 2428 2428 2428 2425 2425 2424 2427 2422 2427 2427 2426 28 2481 100 2410 1981 606 605 604 100 2408 1980 605 1901 1900 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 655 82 557 550 113 113 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ static int sysctl_vfs_cache_pressure __read_mostly = 100; static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); } EXPORT_SYMBOL_GPL(vfs_pressure_ratio); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __ro_after_init; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); static int dentry_negative_policy; #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, { .procname = "dentry-negative", .data = &dentry_negative_policy, .maxlen = sizeof(dentry_negative_policy), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static const struct ctl_table vm_dcache_sysctls[] = { { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "vfs_cache_pressure_denom", .data = &sysctl_vfs_cache_pressure_denom, .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE_HUNDRED, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("vm", vm_dcache_sysctls); register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } /* * long names are allocated separately from dentry and never modified. * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() * for the reason why ->count and ->head can't be combined into a union. * dentry_string_cmp() relies upon ->name[] being word-aligned. */ struct external_name { atomic_t count; struct rcu_head head; unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { unsigned seq; const unsigned char *s; rcu_read_lock(); retry: seq = read_seqcount_begin(&dentry->d_seq); s = READ_ONCE(dentry->d_name.name); name->name.hash_len = dentry->d_name.hash_len; name->name.name = name->inline_name.string; if (likely(s == dentry->d_shortname.string)) { name->inline_name = dentry->d_shortname; } else { struct external_name *p; p = container_of(s, struct external_name, name[0]); // get a valid reference if (unlikely(!atomic_inc_not_zero(&p->count))) goto retry; name->name.name = s; } if (read_seqcount_retry(&dentry->d_seq, seq)) { release_dentry_name_snapshot(name); goto retry; } rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->count))) kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(dput); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, &dispose); spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { spin_lock(&data.victim->d_lock); if (!lock_for_kill(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { shrink_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->count, 1); dname = p->name; } else { dname = dentry->d_shortname.string; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_flags = 0; lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_HLIST_NODE(&dentry->d_sib); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; if (!sb->s_d_op) d_set_d_op(dentry, &anon_ops); } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @parent: parent dentry * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { if (dentry_negative_policy) __d_drop(dentry); dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); if (wq_has_sleeper(d_wait)) wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ dentry->d_name.name = target->d_name.name; target->d_shortname = dentry->d_shortname; target->d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ target->d_name.name = dentry->d_name.name; dentry->d_shortname = target->d_shortname; dentry->d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ for (int i = 0; i < DNAME_INLINE_WORDS; i++) swap(dentry->d_shortname.words[i], target->d_shortname.words[i]); } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->count); dentry->d_name = target->d_name; } else { dentry->d_shortname = target->d_shortname; dentry->d_name.name = dentry->d_shortname.string; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->count))) kfree_rcu(old_name, head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: if (alias->d_op && alias->d_op->d_unalias_trylock && !alias->d_op->d_unalias_trylock(alias)) goto out_err; __d_move(alias, dentry, false); if (alias->d_op && alias->d_op->d_unalias_unlock) alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __ro_after_init; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 4 4 9 1 146 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | // SPDX-License-Identifier: GPL-2.0-or-later /* * UDPLITE An implementation of the UDP-Lite protocol (RFC 3828). * * Authors: Gerrit Renker <gerrit@erg.abdn.ac.uk> * * Changes: * Fixes: */ #define pr_fmt(fmt) "UDPLite: " fmt #include <linux/export.h> #include <linux/proc_fs.h> #include "udp_impl.h" struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table); /* Designate sk as UDP-Lite socket */ static int udplite_sk_init(struct sock *sk) { udp_init_sock(sk); pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, " "please contact the netdev mailing list\n"); return 0; } static int udplite_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); } static int udplite_err(struct sk_buff *skb, u32 info) { return __udp4_lib_err(skb, info, &udplite_table); } static const struct net_protocol udplite_protocol = { .handler = udplite_rcv, .err_handler = udplite_err, .no_policy = 1, }; struct proto udplite_prot = { .name = "UDP-Lite", .owner = THIS_MODULE, .close = udp_lib_close, .connect = ip4_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udplite_sk_init, .destroy = udp_destroy_sock, .setsockopt = udp_setsockopt, .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &net_aligned_data.udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, }; EXPORT_SYMBOL(udplite_prot); static struct inet_protosw udplite4_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_UDPLITE, .prot = &udplite_prot, .ops = &inet_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }; #ifdef CONFIG_PROC_FS static struct udp_seq_afinfo udplite4_seq_afinfo = { .family = AF_INET, .udp_table = &udplite_table, }; static int __net_init udplite4_proc_init_net(struct net *net) { if (!proc_create_net_data("udplite", 0444, net->proc_net, &udp_seq_ops, sizeof(struct udp_iter_state), &udplite4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit udplite4_proc_exit_net(struct net *net) { remove_proc_entry("udplite", net->proc_net); } static struct pernet_operations udplite4_net_ops = { .init = udplite4_proc_init_net, .exit = udplite4_proc_exit_net, }; static __init int udplite4_proc_init(void) { return register_pernet_subsys(&udplite4_net_ops); } #else static inline int udplite4_proc_init(void) { return 0; } #endif void __init udplite4_register(void) { udp_table_init(&udplite_table, "UDP-Lite"); if (proto_register(&udplite_prot, 1)) goto out_register_err; if (inet_add_protocol(&udplite_protocol, IPPROTO_UDPLITE) < 0) goto out_unregister_proto; inet_register_protosw(&udplite4_protosw); if (udplite4_proc_init()) pr_err("%s: Cannot register /proc!\n", __func__); return; out_unregister_proto: proto_unregister(&udplite_prot); out_register_err: pr_crit("%s: Cannot add UDP-Lite protocol\n", __func__); } |
| 5 13 22 79 39 56 69 8 12 27 6 244 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _NET_ETHTOOL_NETLINK_H #define _NET_ETHTOOL_NETLINK_H #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <net/genetlink.h> #include <net/sock.h> struct ethnl_req_info; int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *nest, struct net *net, struct netlink_ext_ack *extack, bool require_dev); int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype); struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp); void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd); void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd); void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd); int ethnl_multicast(struct sk_buff *skb, struct net_device *dev); void ethnl_notify(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *req_info); /** * ethnl_strz_size() - calculate attribute length for fixed size string * @s: ETH_GSTRING_LEN sized string (may not be null terminated) * * Return: total length of an attribute with null terminated string from @s */ static inline int ethnl_strz_size(const char *s) { return nla_total_size(strnlen(s, ETH_GSTRING_LEN) + 1); } /** * ethnl_put_strz() - put string attribute with fixed size string * @skb: skb with the message * @attrtype: attribute type * @s: ETH_GSTRING_LEN sized string (may not be null terminated) * * Puts an attribute with null terminated string from @s into the message. * * Return: 0 on success, negative error code on failure */ static inline int ethnl_put_strz(struct sk_buff *skb, u16 attrtype, const char *s) { unsigned int len = strnlen(s, ETH_GSTRING_LEN); struct nlattr *attr; attr = nla_reserve(skb, attrtype, len + 1); if (!attr) return -EMSGSIZE; memcpy(nla_data(attr), s, len); ((char *)nla_data(attr))[len] = '\0'; return 0; } /** * ethnl_update_u32() - update u32 value from NLA_U32 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Copy the u32 value from NLA_U32 netlink attribute @attr into variable * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod * is set to true if this function changed the value of *dst, otherwise it * is left as is. */ static inline void ethnl_update_u32(u32 *dst, const struct nlattr *attr, bool *mod) { u32 val; if (!attr) return; val = nla_get_u32(attr); if (*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_u8() - update u8 value from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Copy the u8 value from NLA_U8 netlink attribute @attr into variable * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod * is set to true if this function changed the value of *dst, otherwise it * is left as is. */ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr, bool *mod) { u8 val; if (!attr) return; val = nla_get_u8(attr); if (*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Use the u8 value from NLA_U8 netlink attribute @attr to set u32 variable * pointed to by @dst to 0 (if zero) or 1 (if not); do nothing if @attr is * null. Bool pointed to by @mod is set to true if this function changed the * logical value of *dst, otherwise it is left as is. */ static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr, bool *mod) { u8 val; if (!attr) return; val = !!nla_get_u8(attr); if (!!*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_bool() - updateb bool used as bool from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Use the bool value from NLA_U8 netlink attribute @attr to set bool variable * pointed to by @dst to 0 (if zero) or 1 (if not); do nothing if @attr is * null. Bool pointed to by @mod is set to true if this function changed the * logical value of *dst, otherwise it is left as is. */ static inline void ethnl_update_bool(bool *dst, const struct nlattr *attr, bool *mod) { u8 val; if (!attr) return; val = !!nla_get_u8(attr); if (!!*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_binary() - update binary data from NLA_BINARY attribute * @dst: value to update * @len: destination buffer length * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Use the u8 value from NLA_U8 netlink attribute @attr to rewrite data block * of length @len at @dst by attribute payload; do nothing if @attr is null. * Bool pointed to by @mod is set to true if this function changed the logical * value of *dst, otherwise it is left as is. */ static inline void ethnl_update_binary(void *dst, unsigned int len, const struct nlattr *attr, bool *mod) { if (!attr) return; if (nla_len(attr) < len) len = nla_len(attr); if (!memcmp(dst, nla_data(attr), len)) return; memcpy(dst, nla_data(attr), len); *mod = true; } /** * ethnl_update_bitfield32() - update u32 value from NLA_BITFIELD32 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Update bits in u32 value which are set in attribute's mask to values from * attribute's value. Do nothing if @attr is null or the value wouldn't change; * otherwise, set bool pointed to by @mod to true. */ static inline void ethnl_update_bitfield32(u32 *dst, const struct nlattr *attr, bool *mod) { struct nla_bitfield32 change; u32 newval; if (!attr) return; change = nla_get_bitfield32(attr); newval = (*dst & ~change.selector) | (change.value & change.selector); if (*dst == newval) return; *dst = newval; *mod = true; } /** * ethnl_reply_header_size() - total size of reply header * * This is an upper estimate so that we do not need to hold RTNL lock longer * than necessary (to prevent rename between size estimate and composing the * message). Accounts only for device ifindex and name as those are the only * attributes ethnl_fill_reply_header() puts into the reply header. */ static inline unsigned int ethnl_reply_header_size(void) { return nla_total_size(nla_total_size(sizeof(u32)) + nla_total_size(IFNAMSIZ)); } /* GET request handling */ /* Unified processing of GET requests uses two data structures: request info * and reply data. Request info holds information parsed from client request * and its stays constant through all request processing. Reply data holds data * retrieved from ethtool_ops callbacks or other internal sources which is used * to compose the reply. When processing a dump request, request info is filled * only once (when the request message is parsed) but reply data is filled for * each reply message. * * Both structures consist of part common for all request types (struct * ethnl_req_info and struct ethnl_reply_data defined below) and optional * parts specific for each request type. Common part always starts at offset 0. */ /** * struct ethnl_req_info - base type of request information for GET requests * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types * @phy_index: phy_device index connected to @dev this request is for. Can be * 0 if the request doesn't target a phy, or if the @dev's attached * phy is targeted. * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at * zero offset. */ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; u32 phy_index; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) { netdev_put(req_info->dev, &req_info->dev_tracker); } /** * ethnl_req_get_phydev() - Gets the phy_device targeted by this request, * if any. Must be called under rntl_lock(). * @req_info: The ethnl request to get the phy from. * @tb: The netlink attributes array, for error reporting. * @header: The netlink header index, used for error reporting. * @extack: The netlink extended ACK, for error reporting. * * The caller must hold RTNL, until it's done interacting with the returned * phy_device. * * Return: A phy_device pointer corresponding either to the passed phy_index * if one is provided. If not, the phy_device attached to the * net_device targeted by this request is returned. If there's no * targeted net_device, or no phy_device is attached, NULL is * returned. If the provided phy_index is invalid, an error pointer * is returned. */ struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, struct nlattr **tb, unsigned int header, struct netlink_ext_ack *extack); /** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is * equal to ðnl_req_info.dev; in dumps it's different for each * reply message * * This is a common base for request specific structures holding data for * kernel reply message. These always embed struct ethnl_reply_data at zero * offset. */ struct ethnl_reply_data { struct net_device *dev; }; int ethnl_ops_begin(struct net_device *dev); void ethnl_ops_complete(struct net_device *dev); enum ethnl_sock_type { ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH, }; struct ethnl_sock_priv { struct net_device *dev; u32 portid; enum ethnl_sock_type type; }; int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, enum ethnl_sock_type type); /** * struct ethnl_request_ops - unified handling of GET and SET requests * @request_cmd: command id for request (GET) * @reply_cmd: command id for reply (GET_REPLY) * @hdr_attr: attribute type for request header * @req_info_size: size of request info * @reply_data_size: size of reply data * @allow_nodev_do: allow non-dump request with no device identification * @set_ntf_cmd: notification to generate on changes (SET) * @parse_request: * Parse request except common header (struct ethnl_req_info). Common * header is already filled on entry, the rest up to @repdata_offset * is zero initialized. This callback should only modify type specific * request info by parsed attributes from request message. * Called for both GET and SET. Information parsed for SET will * be conveyed to the req_info used during NTF generation. * @prepare_data: * Retrieve and prepare data needed to compose a reply message. Calls to * ethtool_ops handlers are limited to this callback. Common reply data * (struct ethnl_reply_data) is filled on entry, type specific part after * it is zero initialized. This callback should only modify the type * specific part of reply data. Device identification from struct * ethnl_reply_data is to be used as for dump requests, it iterates * through network devices while dev member of struct ethnl_req_info * points to the device from client request. * @reply_size: * Estimate reply message size. Returned value must be sufficient for * message payload without common reply header. The callback may returned * estimate higher than actual message size if exact calculation would * not be worth the saved memory space. * @fill_reply: * Fill reply message payload (except for common header) from reply data. * The callback must not generate more payload than previously called * ->reply_size() estimated. * @cleanup_data: * Optional cleanup called when reply data is no longer needed. Can be * used e.g. to free any additional data structures outside the main * structure which were allocated by ->prepare_data(). When processing * dump requests, ->cleanup() is called for each message. * @set_validate: * Check if set operation is supported for a given device, and perform * extra input checks. Expected return values: * - 0 if the operation is a noop for the device (rare) * - 1 if operation should proceed to calling @set * - negative errno on errors * Called without any locks, just a reference on the netdev. * @set: * Execute the set operation. The implementation should return * - 0 if no configuration has changed * - 1 if configuration changed and notification should be generated * - negative errno on errors * * Description of variable parts of GET request handling when using the * unified infrastructure. When used, a pointer to an instance of this * structure is to be added to ðnl_default_requests array and generic * handlers ethnl_default_doit(), ethnl_default_dumpit(), * ethnl_default_start() and ethnl_default_done() used in @ethtool_genl_ops; * ethnl_default_notify() can be used in @ethnl_notify_handlers to send * notifications of the corresponding type. */ struct ethnl_request_ops { u8 request_cmd; u8 reply_cmd; u16 hdr_attr; unsigned int req_info_size; unsigned int reply_data_size; bool allow_nodev_do; u8 set_ntf_cmd; int (*parse_request)(struct ethnl_req_info *req_info, struct nlattr **tb, struct netlink_ext_ack *extack); int (*prepare_data)(const struct ethnl_req_info *req_info, struct ethnl_reply_data *reply_data, const struct genl_info *info); int (*reply_size)(const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data); int (*fill_reply)(struct sk_buff *skb, const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data); void (*cleanup_data)(struct ethnl_reply_data *reply_data); int (*set_validate)(struct ethnl_req_info *req_info, struct genl_info *info); int (*set)(struct ethnl_req_info *req_info, struct genl_info *info); }; /* request handlers */ extern const struct ethnl_request_ops ethnl_strset_request_ops; extern const struct ethnl_request_ops ethnl_linkinfo_request_ops; extern const struct ethnl_request_ops ethnl_linkmodes_request_ops; extern const struct ethnl_request_ops ethnl_linkstate_request_ops; extern const struct ethnl_request_ops ethnl_debug_request_ops; extern const struct ethnl_request_ops ethnl_wol_request_ops; extern const struct ethnl_request_ops ethnl_features_request_ops; extern const struct ethnl_request_ops ethnl_privflags_request_ops; extern const struct ethnl_request_ops ethnl_rings_request_ops; extern const struct ethnl_request_ops ethnl_channels_request_ops; extern const struct ethnl_request_ops ethnl_coalesce_request_ops; extern const struct ethnl_request_ops ethnl_pause_request_ops; extern const struct ethnl_request_ops ethnl_eee_request_ops; extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct ethnl_request_ops ethnl_pse_request_ops; extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct ethnl_request_ops ethnl_tsconfig_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1]; extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_LANES + 1]; extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1]; extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1]; extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1]; extern const struct nla_policy ethnl_wol_get_policy[ETHTOOL_A_WOL_HEADER + 1]; extern const struct nla_policy ethnl_wol_set_policy[ETHTOOL_A_WOL_SOPASS + 1]; extern const struct nla_policy ethnl_features_get_policy[ETHTOOL_A_FEATURES_HEADER + 1]; extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANTED + 1]; extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_HDS_THRESH_MAX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1]; extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_STATS_SRC + 1]; extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_STATS_SRC + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1]; extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1]; extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1]; extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1]; extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1]; extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; extern const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1]; extern const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info); int ethnl_rss_dump_start(struct netlink_callback *cb); int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_tsinfo_start(struct netlink_callback *cb); int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_tsinfo_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_mac_names[__ETHTOOL_A_STATS_ETH_MAC_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_ctrl_names[__ETHTOOL_A_STATS_ETH_CTRL_CNT][ETH_GSTRING_LEN]; extern const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN]; extern const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN]; #endif /* _NET_ETHTOOL_NETLINK_H */ |
| 295 377 377 379 378 378 380 379 380 347 218 380 5 380 380 296 295 296 297 297 296 297 295 297 380 296 297 297 380 380 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | // SPDX-License-Identifier: GPL-2.0 /* * FPU signal frame handling routines. */ #include <linux/compat.h> #include <linux/cpu.h> #include <linux/pagemap.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> #include <asm/fpu/xstate.h> #include <asm/sigframe.h> #include <asm/trapnr.h> #include <asm/trace/fpu.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" /* * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, struct _fpx_sw_bytes *fx_sw) { void __user *fpstate = fxbuf; unsigned int magic2; if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw))) return false; /* Check for the first magic field */ if (fx_sw->magic1 != FP_XSTATE_MAGIC1) goto setfx; /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ if (__get_user(magic2, (__u32 __user *)(fpstate + x86_task_fpu(current)->fpstate->user_size))) return false; if (likely(magic2 == FP_XSTATE_MAGIC2)) return true; setfx: trace_x86_fpu_xstate_check_failed(x86_task_fpu(current)); /* Set the parameters for fx only state */ fx_sw->magic1 = 0; fx_sw->xstate_size = sizeof(struct fxregs_state); fx_sw->xfeatures = XFEATURE_MASK_FPSSE; return true; } /* * Signal frame handlers. */ static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf) { if (use_fxsr()) { struct xregs_state *xsave = &x86_task_fpu(tsk)->fpstate->regs.xsave; struct user_i387_ia32_struct env; struct _fpstate_32 __user *fp = buf; fpregs_lock(); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) fxsave(&x86_task_fpu(tsk)->fpstate->regs.fxsave); fpregs_unlock(); convert_from_fxsr(&env, tsk); if (__copy_to_user(buf, &env, sizeof(env)) || __put_user(xsave->i387.swd, &fp->status) || __put_user(X86_FXSR_MAGIC, &fp->magic)) return false; } else { struct fregs_state __user *fp = buf; u32 swd; if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) return false; } return true; } /* * Prepare the SW reserved portion of the fxsave memory layout, indicating * the presence of the extended state information in the memory layout * pointed to by the fpstate pointer in the sigcontext. * This is saved when ever the FP and extended state context is * saved on the user stack during the signal handler delivery to the user. */ static inline void save_sw_bytes(struct _fpx_sw_bytes *sw_bytes, bool ia32_frame, struct fpstate *fpstate) { sw_bytes->magic1 = FP_XSTATE_MAGIC1; sw_bytes->extended_size = fpstate->user_size + FP_XSTATE_MAGIC2_SIZE; sw_bytes->xfeatures = fpstate->user_xfeatures; sw_bytes->xstate_size = fpstate->user_size; if (ia32_frame) sw_bytes->extended_size += sizeof(struct fregs_state); } static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; struct _fpx_sw_bytes sw_bytes = {}; int err; /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ save_sw_bytes(&sw_bytes, ia32_frame, fpstate); err = __copy_to_user(&x->i387.sw_reserved, &sw_bytes, sizeof(sw_bytes)); if (!use_xsave()) return !err; err |= __put_user(FP_XSTATE_MAGIC2, (__u32 __user *)(buf + fpstate->user_size)); /* * For legacy compatible, we always set FP/SSE bits in the bit * vector while saving the state to the user context. This will * enable us capturing any changes(during sigreturn) to * the FP/SSE bits by the legacy applications which don't touch * xfeatures in the xsave header. * * xsave aware apps can change the xfeatures in the xsave * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE); return !err; } static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru) { if (use_xsave()) return xsave_to_user_sigframe(buf, pkru); if (use_fxsr()) return fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else return fnsave_to_user_sigframe((struct fregs_state __user *) buf); } /* * Save the fpu, extended register state to the user signal frame. * * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save * state is copied. * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. * * buf == buf_fx for 64-bit frames and 32-bit fsave frame. * buf != buf_fx for 32-bit frames with fxstate. * * Save it directly to the user frame with disabled page fault handler. If * that faults, try to clear the frame which handles the page fault. * * If this is a 32-bit frame with fxstate, put a fsave header before * the aligned state at 'buf_fx'. * * For [f]xsave state, update the SW reserved fields in the [f]xsave frame * indicating the absence/presence of the extended state to the user. */ bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru) { struct task_struct *tsk = current; struct fpstate *fpstate = x86_task_fpu(tsk)->fpstate; bool ia32_fxstate = (buf != buf_fx); int ret; ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) || IS_ENABLED(CONFIG_IA32_EMULATION)); if (!static_cpu_has(X86_FEATURE_FPU)) { struct user_i387_ia32_struct fp; fpregs_soft_get(current, NULL, (struct membuf){.p = &fp, .left = sizeof(fp)}); return !copy_to_user(buf, &fp, sizeof(fp)); } if (!access_ok(buf, size)) return false; if (use_xsave()) { struct xregs_state __user *xbuf = buf_fx; /* * Clear the xsave header first, so that reserved fields are * initialized to zero. */ if (__clear_user(&xbuf->header, sizeof(xbuf->header))) return false; } retry: /* * Load the FPU registers if they are not valid for the current task. * With a valid FPU state we can attempt to save the state directly to * userland's stack frame which will likely succeed. If it does not, * resolve the fault in the user memory and try again. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); pagefault_disable(); ret = copy_fpregs_to_sigframe(buf_fx, pkru); pagefault_enable(); fpregs_unlock(); if (ret) { if (!__clear_user(buf_fx, fpstate->user_size)) goto retry; return false; } /* Save the fsave header for the 32-bit frames. */ if ((ia32_fxstate || !use_fxsr()) && !save_fsave_header(tsk, buf)) return false; if (use_fxsr() && !save_xstate_epilog(buf_fx, ia32_fxstate, fpstate)) return false; return true; } static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, u64 xrestore, bool fx_only) { if (use_xsave()) { u64 init_bv = ufeatures & ~xrestore; int ret; if (likely(!fx_only)) ret = xrstor_from_user_sigframe(buf, xrestore); else ret = fxrstor_from_user_sigframe(buf); if (!ret && unlikely(init_bv)) os_xrstor(&init_fpstate, init_bv); return ret; } else if (use_fxsr()) { return fxrstor_from_user_sigframe(buf); } else { return frstor_from_user_sigframe(buf); } } /* * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = x86_task_fpu(current); int ret; /* Restore enabled features only. */ xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ xfd_update_state(fpu->fpstate); pagefault_disable(); ret = __restore_fpregs_from_user(buf, fpu->fpstate->user_xfeatures, xrestore, fx_only); pagefault_enable(); if (unlikely(ret)) { /* * The above did an FPU restore operation, restricted to * the user portion of the registers, and failed, but the * microcode might have modified the FPU registers * nevertheless. * * If the FPU registers do not belong to current, then * invalidate the FPU register state otherwise the task * might preempt current and return to user space with * corrupted FPU registers. */ if (test_thread_flag(TIF_NEED_FPU_LOAD)) __cpu_invalidate_fpregs_state(); fpregs_unlock(); /* Try to handle #PF, but anything else is fatal. */ if (ret != X86_TRAP_PF) return false; if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } /* * Restore supervisor states: previous context switch etc has done * XSAVES and saved the supervisor states in the kernel buffer from * which they can be restored now. * * It would be optimal to handle this with a single XRSTORS, but * this does not work because the rest of the FPU registers have * been restored from a user buffer directly. */ if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor()) os_xrstor_supervisor(fpu->fpstate); fpregs_mark_activate(); fpregs_unlock(); return true; } static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, bool ia32_fxstate) { struct task_struct *tsk = current; struct fpu *fpu = x86_task_fpu(tsk); struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; u64 user_xfeatures = 0; if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; if (!check_xstate_in_sigframe(buf_fx, &fx_sw_user)) return false; fx_only = !fx_sw_user.magic1; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* * Copy the legacy state because the FP portion of the FX frame has * to be ignored for histerical raisins. The legacy state is folded * in once the larger state has been copied. */ if (__copy_from_user(&env, buf, sizeof(env))) return false; /* * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is * not modified on context switch and that the xstate is considered * to be loaded again on return to userland (overriding last_cpu avoids * the optimisation). */ fpregs_lock(); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { /* * If supervisor states are available then save the * hardware state in current's fpstate so that the * supervisor state is preserved. Save the full state for * simplicity. There is no point in optimizing this by only * saving the supervisor states and then shuffle them to * the right place in memory. It's ia32 mode. Shrug. */ if (xfeatures_mask_supervisor()) os_xsave(fpu->fpstate); set_thread_flag(TIF_NEED_FPU_LOAD); } __fpu_invalidate_fpregs_state(fpu); __cpu_invalidate_fpregs_state(); fpregs_unlock(); fpregs = &fpu->fpstate->regs; if (use_xsave() && !fx_only) { if (copy_sigframe_from_user_to_xstate(tsk, buf_fx)) return false; } else { if (__copy_from_user(&fpregs->fxsave, buf_fx, sizeof(fpregs->fxsave))) return false; if (IS_ENABLED(CONFIG_X86_64)) { /* Reject invalid MXCSR values. */ if (fpregs->fxsave.mxcsr & ~mxcsr_feature_mask) return false; } else { /* Mask invalid bits out for historical reasons (broken hardware). */ fpregs->fxsave.mxcsr &= mxcsr_feature_mask; } /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */ if (use_xsave()) fpregs->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; } /* Fold the legacy FP storage */ convert_to_fxsr(&fpregs->fxsave, &env); fpregs_lock(); if (use_xsave()) { /* * Remove all UABI feature bits not set in user_xfeatures * from the memory xstate header which makes the full * restore below bring them into init state. This works for * fx_only mode as well because that has only FP and SSE * set in user_xfeatures. * * Preserve supervisor states! */ u64 mask = user_xfeatures | xfeatures_mask_supervisor(); fpregs->xsave.header.xfeatures &= mask; success = !os_xrstor_safe(fpu->fpstate, fpu_kernel_cfg.max_features); } else { success = !fxrstor_safe(&fpregs->fxsave); } if (likely(success)) fpregs_mark_activate(); fpregs_unlock(); return success; } static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate) { unsigned int size = fpstate->user_size; return use_xsave() ? size + FP_XSTATE_MAGIC2_SIZE : size; } /* * Restore FPU state from a sigframe: */ bool fpu__restore_sig(void __user *buf, int ia32_frame) { struct fpu *fpu = x86_task_fpu(current); void __user *buf_fx = buf; bool ia32_fxstate = false; bool success = false; unsigned int size; if (unlikely(!buf)) { fpu__clear_user_states(fpu); return true; } size = xstate_sigframe_size(fpu->fpstate); ia32_frame &= (IS_ENABLED(CONFIG_X86_32) || IS_ENABLED(CONFIG_IA32_EMULATION)); /* * Only FXSR enabled systems need the FX state quirk. * FRSTOR does not need it and can use the fast path. */ if (ia32_frame && use_fxsr()) { buf_fx = buf + sizeof(struct fregs_state); size += sizeof(struct fregs_state); ia32_fxstate = true; } if (!access_ok(buf, size)) goto out; if (!IS_ENABLED(CONFIG_X86_64) && !cpu_feature_enabled(X86_FEATURE_FPU)) { success = !fpregs_soft_set(current, NULL, 0, sizeof(struct user_i387_ia32_struct), NULL, buf); } else { success = __fpu_restore_sig(buf, buf_fx, ia32_fxstate); } out: if (unlikely(!success)) fpu__clear_user_states(fpu); return success; } unsigned long fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, unsigned long *size) { unsigned long frame_size = xstate_sigframe_size(x86_task_fpu(current)->fpstate); *buf_fx = sp = round_down(sp - frame_size, 64); if (ia32_frame && use_fxsr()) { frame_size += sizeof(struct fregs_state); sp -= sizeof(struct fregs_state); } *size = frame_size; return sp; } unsigned long __init fpu__get_fpstate_size(void) { unsigned long ret = fpu_user_cfg.max_size; if (use_xsave()) ret += FP_XSTATE_MAGIC2_SIZE; /* * This space is needed on (most) 32-bit kernels, or when a 32-bit * app is running on a 64-bit kernel. To keep things simple, just * assume the worst case and always include space for 'freg_state', * even for 64-bit apps on 64-bit kernels. This wastes a bit of * space, but keeps the code simple. */ if ((IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) && use_fxsr()) ret += sizeof(struct fregs_state); return ret; } |
| 5167 7440 1464 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 4 5 5 5 3 1 5 9 9 9 3 6 9 9 6 6 3 3 3 3 3 9 10 5 5 5 5 5 5 14 2 1 1 1 9 9 9 5 4 3 6 5 9 3 1 1 1 4 2 1 1 1 1 1 1 18 1 1 4 4 2 10 10 2 5 5 5 1 5 5 5 5 5 1 15 15 4 13 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_gred.c Generic Random Early Detection queue. * * Authors: J Hadi Salim (hadi@cyberus.ca) 1998-2002 * * 991129: - Bug fix with grio mode * - a better sing. AvgQ mode with Grio(WRED) * - A finer grained VQ dequeue based on suggestion * from Ren Liu * - More error checks * * For all the glorious comments look at include/net/red.h */ #include <linux/slab.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/red.h> #define GRED_DEF_PRIO (MAX_DPs / 2) #define GRED_VQ_MASK (MAX_DPs - 1) #define GRED_VQ_RED_FLAGS (TC_RED_ECN | TC_RED_HARDDROP) struct gred_sched_data; struct gred_sched; struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop parameters */ u32 red_flags; /* virtualQ version of red_flags */ u64 bytesin; /* bytes seen on virtualQ so far*/ u32 packetsin; /* packets seen on virtualQ so far*/ u32 backlog; /* bytes on the virtualQ */ u8 prio; /* the prio of this vq */ struct red_parms parms; struct red_vars vars; struct red_stats stats; }; enum { GRED_WRED_MODE = 1, GRED_RIO_MODE, }; struct gred_sched { struct gred_sched_data *tab[MAX_DPs]; unsigned long flags; u32 red_flags; u32 DPs; u32 def; struct red_vars wred_set; struct tc_gred_qopt_offload *opt; }; static inline int gred_wred_mode(struct gred_sched *table) { return test_bit(GRED_WRED_MODE, &table->flags); } static inline void gred_enable_wred_mode(struct gred_sched *table) { __set_bit(GRED_WRED_MODE, &table->flags); } static inline void gred_disable_wred_mode(struct gred_sched *table) { __clear_bit(GRED_WRED_MODE, &table->flags); } static inline int gred_rio_mode(struct gred_sched *table) { return test_bit(GRED_RIO_MODE, &table->flags); } static inline void gred_enable_rio_mode(struct gred_sched *table) { __set_bit(GRED_RIO_MODE, &table->flags); } static inline void gred_disable_rio_mode(struct gred_sched *table) { __clear_bit(GRED_RIO_MODE, &table->flags); } static inline int gred_wred_mode_check(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); int i; /* Really ugly O(n^2) but shouldn't be necessary too frequent. */ for (i = 0; i < table->DPs; i++) { struct gred_sched_data *q = table->tab[i]; int n; if (q == NULL) continue; for (n = i + 1; n < table->DPs; n++) if (table->tab[n] && table->tab[n]->prio == q->prio) return 1; } return 0; } static inline unsigned int gred_backlog(struct gred_sched *table, struct gred_sched_data *q, struct Qdisc *sch) { if (gred_wred_mode(table)) return sch->qstats.backlog; else return q->backlog; } static inline u16 tc_index_to_dp(struct sk_buff *skb) { return skb->tc_index & GRED_VQ_MASK; } static inline void gred_load_wred_set(const struct gred_sched *table, struct gred_sched_data *q) { q->vars.qavg = table->wred_set.qavg; q->vars.qidlestart = table->wred_set.qidlestart; } static inline void gred_store_wred_set(struct gred_sched *table, struct gred_sched_data *q) { table->wred_set.qavg = q->vars.qavg; table->wred_set.qidlestart = q->vars.qidlestart; } static int gred_use_ecn(struct gred_sched_data *q) { return q->red_flags & TC_RED_ECN; } static int gred_use_harddrop(struct gred_sched_data *q) { return q->red_flags & TC_RED_HARDDROP; } static bool gred_per_vq_red_flags_used(struct gred_sched *table) { unsigned int i; /* Local per-vq flags couldn't have been set unless global are 0 */ if (table->red_flags) return false; for (i = 0; i < MAX_DPs; i++) if (table->tab[i] && table->tab[i]->red_flags) return true; return false; } static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct gred_sched_data *q = NULL; struct gred_sched *t = qdisc_priv(sch); unsigned long qavg = 0; u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { dp = t->def; q = t->tab[dp]; if (!q) { /* Pass through packets not assigned to a DP * if no default DP has been configured. This * allows for DP flows to be left untouched. */ if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) return qdisc_enqueue_tail(skb, sch); else goto drop; } /* fix tc_index? --could be controversial but needed for requeueing */ skb->tc_index = (skb->tc_index & ~GRED_VQ_MASK) | dp; } /* sum up all the qaves of prios < ours to get the new qave */ if (!gred_wred_mode(t) && gred_rio_mode(t)) { int i; for (i = 0; i < t->DPs; i++) { if (t->tab[i] && t->tab[i]->prio < q->prio && !red_is_idling(&t->tab[i]->vars)) qavg += t->tab[i]->vars.qavg; } } q->packetsin++; q->bytesin += qdisc_pkt_len(skb); if (gred_wred_mode(t)) gred_load_wred_set(t, q); q->vars.qavg = red_calc_qavg(&q->parms, &q->vars, gred_backlog(t, q, sch)); if (red_is_idling(&q->vars)) red_end_of_idle_period(&q->vars); if (gred_wred_mode(t)) gred_store_wred_set(t, q); switch (red_action(&q->parms, &q->vars, q->vars.qavg + qavg)) { case RED_DONT_MARK: break; case RED_PROB_MARK: qdisc_qstats_overlimit(sch); if (!gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } q->stats.prob_mark++; break; case RED_HARD_MARK: qdisc_qstats_overlimit(sch); if (gred_use_harddrop(q) || !gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; } q->stats.forced_mark++; break; } if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) { q->backlog += qdisc_pkt_len(skb); return qdisc_enqueue_tail(skb, sch); } q->stats.pdrop++; drop: return qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); congestion_drop: qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_CONGESTED); return NET_XMIT_CN; } static struct sk_buff *gred_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); skb = qdisc_dequeue_head(sch); if (skb) { struct gred_sched_data *q; u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x after dequeue, screwing up backlog\n", tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); if (gred_wred_mode(t)) { if (!sch->qstats.backlog) red_start_of_idle_period(&t->wred_set); } else { if (!q->backlog) red_start_of_idle_period(&q->vars); } } return skb; } return NULL; } static void gred_reset(struct Qdisc *sch) { int i; struct gred_sched *t = qdisc_priv(sch); qdisc_reset_queue(sch); for (i = 0; i < t->DPs; i++) { struct gred_sched_data *q = t->tab[i]; if (!q) continue; red_restart(&q->vars); q->backlog = 0; } } static void gred_offload(struct Qdisc *sch, enum tc_gred_command command) { struct gred_sched *table = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_gred_qopt_offload *opt = table->opt; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; memset(opt, 0, sizeof(*opt)); opt->command = command; opt->handle = sch->handle; opt->parent = sch->parent; if (command == TC_GRED_REPLACE) { unsigned int i; opt->set.grio_on = gred_rio_mode(table); opt->set.wred_on = gred_wred_mode(table); opt->set.dp_cnt = table->DPs; opt->set.dp_def = table->def; for (i = 0; i < table->DPs; i++) { struct gred_sched_data *q = table->tab[i]; if (!q) continue; opt->set.tab[i].present = true; opt->set.tab[i].limit = q->limit; opt->set.tab[i].prio = q->prio; opt->set.tab[i].min = q->parms.qth_min >> q->parms.Wlog; opt->set.tab[i].max = q->parms.qth_max >> q->parms.Wlog; opt->set.tab[i].is_ecn = gred_use_ecn(q); opt->set.tab[i].is_harddrop = gred_use_harddrop(q); opt->set.tab[i].probability = q->parms.max_P; opt->set.tab[i].backlog = &q->backlog; } opt->set.qstats = &sch->qstats; } dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, opt); } static int gred_offload_dump_stats(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt_offload *hw_stats; u64 bytes = 0, packets = 0; unsigned int i; int ret; hw_stats = kzalloc(sizeof(*hw_stats), GFP_KERNEL); if (!hw_stats) return -ENOMEM; hw_stats->command = TC_GRED_STATS; hw_stats->handle = sch->handle; hw_stats->parent = sch->parent; for (i = 0; i < MAX_DPs; i++) { gnet_stats_basic_sync_init(&hw_stats->stats.bstats[i]); if (table->tab[i]) hw_stats->stats.xstats[i] = &table->tab[i]->stats; } ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); /* Even if driver returns failure adjust the stats - in case offload * ended but driver still wants to adjust the values. */ sch_tree_lock(sch); for (i = 0; i < MAX_DPs; i++) { if (!table->tab[i]) continue; table->tab[i]->packetsin += u64_stats_read(&hw_stats->stats.bstats[i].packets); table->tab[i]->bytesin += u64_stats_read(&hw_stats->stats.bstats[i].bytes); table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; bytes += u64_stats_read(&hw_stats->stats.bstats[i].bytes); packets += u64_stats_read(&hw_stats->stats.bstats[i].packets); sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; sch->qstats.drops += hw_stats->stats.qstats[i].drops; sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; } _bstats_update(&sch->bstats, bytes, packets); sch_tree_unlock(sch); kfree(hw_stats); return ret; } static inline void gred_destroy_vq(struct gred_sched_data *q) { kfree(q); } static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_sopt *sopt; bool red_flags_changed; int i; if (!dps) return -EINVAL; sopt = nla_data(dps); if (sopt->DPs > MAX_DPs) { NL_SET_ERR_MSG_MOD(extack, "number of virtual queues too high"); return -EINVAL; } if (sopt->DPs == 0) { NL_SET_ERR_MSG_MOD(extack, "number of virtual queues can't be 0"); return -EINVAL; } if (sopt->def_DP >= sopt->DPs) { NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count"); return -EINVAL; } if (sopt->flags && gred_per_vq_red_flags_used(table)) { NL_SET_ERR_MSG_MOD(extack, "can't set per-Qdisc RED flags when per-virtual queue flags are used"); return -EINVAL; } sch_tree_lock(sch); table->DPs = sopt->DPs; table->def = sopt->def_DP; red_flags_changed = table->red_flags != sopt->flags; table->red_flags = sopt->flags; /* * Every entry point to GRED is synchronized with the above code * and the DP is checked against DPs, i.e. shadowed VQs can no * longer be found so we can unlock right here. */ sch_tree_unlock(sch); if (sopt->grio) { gred_enable_rio_mode(table); gred_disable_wred_mode(table); if (gred_wred_mode_check(sch)) gred_enable_wred_mode(table); } else { gred_disable_rio_mode(table); gred_disable_wred_mode(table); } if (red_flags_changed) for (i = 0; i < table->DPs; i++) if (table->tab[i]) table->tab[i]->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } } gred_offload(sch, TC_GRED_REPLACE); return 0; } static inline int gred_change_vq(struct Qdisc *sch, int dp, struct tc_gred_qopt *ctl, int prio, u8 *stab, u32 max_P, struct gred_sched_data **prealloc, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } if (!q) { table->tab[dp] = q = *prealloc; *prealloc = NULL; if (!q) return -ENOMEM; q->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; } q->DP = dp; q->prio = prio; if (ctl->limit > sch->limit) q->limit = sch->limit; else q->limit = ctl->limit; if (q->backlog == 0) red_end_of_idle_period(&q->vars); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, stab, max_P); red_set_vars(&q->vars); return 0; } static const struct nla_policy gred_vq_policy[TCA_GRED_VQ_MAX + 1] = { [TCA_GRED_VQ_DP] = { .type = NLA_U32 }, [TCA_GRED_VQ_FLAGS] = { .type = NLA_U32 }, }; static const struct nla_policy gred_vqe_policy[TCA_GRED_VQ_ENTRY_MAX + 1] = { [TCA_GRED_VQ_ENTRY] = { .type = NLA_NESTED }, }; static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_PARMS] = { .len = sizeof(struct tc_gred_qopt) }, [TCA_GRED_STAB] = { .len = 256 }, [TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) }, [TCA_GRED_MAX_P] = { .type = NLA_U32 }, [TCA_GRED_LIMIT] = { .type = NLA_U32 }, [TCA_GRED_VQ_LIST] = { .type = NLA_NESTED }, }; static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry) { struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; u32 dp; nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, NULL); dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); if (tb[TCA_GRED_VQ_FLAGS]) table->tab[dp]->red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); } static void gred_vqs_apply(struct gred_sched *table, struct nlattr *vqs) { const struct nlattr *attr; int rem; nla_for_each_nested(attr, vqs, rem) { switch (nla_type(attr)) { case TCA_GRED_VQ_ENTRY: gred_vq_apply(table, attr); break; } } } static int gred_vq_validate(struct gred_sched *table, u32 cdp, const struct nlattr *entry, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; int err; u32 dp; err = nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, extack); if (err < 0) return err; if (!tb[TCA_GRED_VQ_DP]) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue with no index specified"); return -EINVAL; } dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); if (dp >= table->DPs) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue with index out of bounds"); return -EINVAL; } if (dp != cdp && !table->tab[dp]) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue not yet instantiated"); return -EINVAL; } if (tb[TCA_GRED_VQ_FLAGS]) { u32 red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); if (table->red_flags && table->red_flags != red_flags) { NL_SET_ERR_MSG_MOD(extack, "can't change per-virtual queue RED flags when per-Qdisc flags are used"); return -EINVAL; } if (red_flags & ~GRED_VQ_RED_FLAGS) { NL_SET_ERR_MSG_MOD(extack, "invalid RED flags specified"); return -EINVAL; } } return 0; } static int gred_vqs_validate(struct gred_sched *table, u32 cdp, struct nlattr *vqs, struct netlink_ext_ack *extack) { const struct nlattr *attr; int rem, err; err = nla_validate_nested_deprecated(vqs, TCA_GRED_VQ_ENTRY_MAX, gred_vqe_policy, extack); if (err < 0) return err; nla_for_each_nested(attr, vqs, rem) { switch (nla_type(attr)) { case TCA_GRED_VQ_ENTRY: err = gred_vq_validate(table, cdp, attr, extack); if (err) return err; break; default: NL_SET_ERR_MSG_MOD(extack, "GRED_VQ_LIST can contain only entry attributes"); return -EINVAL; } } if (rem > 0) { NL_SET_ERR_MSG_MOD(extack, "Trailing data after parsing virtual queue list"); return -EINVAL; } return 0; } static int gred_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt *ctl; struct nlattr *tb[TCA_GRED_MAX + 1]; int err, prio = GRED_DEF_PRIO; u8 *stab; u32 max_P; struct gred_sched_data *prealloc; err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) { if (tb[TCA_GRED_LIMIT] != NULL) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } if (tb[TCA_GRED_PARMS] == NULL || tb[TCA_GRED_STAB] == NULL || tb[TCA_GRED_LIMIT] != NULL) { NL_SET_ERR_MSG_MOD(extack, "can't configure Qdisc and virtual queue at the same time"); return -EINVAL; } max_P = nla_get_u32_default(tb[TCA_GRED_MAX_P], 0); ctl = nla_data(tb[TCA_GRED_PARMS]); stab = nla_data(tb[TCA_GRED_STAB]); if (ctl->DP >= table->DPs) { NL_SET_ERR_MSG_MOD(extack, "virtual queue index above virtual queue count"); return -EINVAL; } if (tb[TCA_GRED_VQ_LIST]) { err = gred_vqs_validate(table, ctl->DP, tb[TCA_GRED_VQ_LIST], extack); if (err) return err; } if (gred_rio_mode(table)) { if (ctl->prio == 0) { int def_prio = GRED_DEF_PRIO; if (table->tab[table->def]) def_prio = table->tab[table->def]->prio; printk(KERN_DEBUG "GRED: DP %u does not have a prio " "setting default to %d\n", ctl->DP, def_prio); prio = def_prio; } else prio = ctl->prio; } prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); sch_tree_lock(sch); err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc, extack); if (err < 0) goto err_unlock_free; if (tb[TCA_GRED_VQ_LIST]) gred_vqs_apply(table, tb[TCA_GRED_VQ_LIST]); if (gred_rio_mode(table)) { gred_disable_wred_mode(table); if (gred_wred_mode_check(sch)) gred_enable_wred_mode(table); } sch_tree_unlock(sch); kfree(prealloc); gred_offload(sch, TC_GRED_REPLACE); return 0; err_unlock_free: sch_tree_unlock(sch); kfree(prealloc); return err; } static int gred_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct nlattr *tb[TCA_GRED_MAX + 1]; int err; if (!opt) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) { NL_SET_ERR_MSG_MOD(extack, "virtual queue configuration can't be specified at initialization time"); return -EINVAL; } if (tb[TCA_GRED_LIMIT]) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); else sch->limit = qdisc_dev(sch)->tx_queue_len * psched_mtu(qdisc_dev(sch)); if (qdisc_dev(sch)->netdev_ops->ndo_setup_tc) { table->opt = kzalloc(sizeof(*table->opt), GFP_KERNEL); if (!table->opt) return -ENOMEM; } return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) { struct gred_sched *table = qdisc_priv(sch); struct nlattr *parms, *vqs, *opts = NULL; int i; u32 max_p[MAX_DPs]; struct tc_gred_sopt sopt = { .DPs = table->DPs, .def_DP = table->def, .grio = gred_rio_mode(table), .flags = table->red_flags, }; if (gred_offload_dump_stats(sch)) goto nla_put_failure; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt)) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; max_p[i] = q ? q->parms.max_P : 0; } if (nla_put(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit)) goto nla_put_failure; /* Old style all-in-one dump of VQs */ parms = nla_nest_start_noflag(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; struct tc_gred_qopt opt; unsigned long qavg; memset(&opt, 0, sizeof(opt)); if (!q) { /* hack -- fix at some point with proper message This is how we indicate to tc that there is no VQ at this DP */ opt.DP = MAX_DPs + i; goto append_opt; } opt.limit = q->limit; opt.DP = q->DP; opt.backlog = gred_backlog(table, q, sch); opt.prio = q->prio; opt.qth_min = q->parms.qth_min >> q->parms.Wlog; opt.qth_max = q->parms.qth_max >> q->parms.Wlog; opt.Wlog = q->parms.Wlog; opt.Plog = q->parms.Plog; opt.Scell_log = q->parms.Scell_log; opt.early = q->stats.prob_drop; opt.forced = q->stats.forced_drop; opt.pdrop = q->stats.pdrop; opt.packets = q->packetsin; opt.bytesin = q->bytesin; if (gred_wred_mode(table)) gred_load_wred_set(table, q); qavg = red_calc_qavg(&q->parms, &q->vars, q->vars.qavg >> q->parms.Wlog); opt.qave = qavg >> q->parms.Wlog; append_opt: if (nla_append(skb, sizeof(opt), &opt) < 0) goto nla_put_failure; } nla_nest_end(skb, parms); /* Dump the VQs again, in more structured way */ vqs = nla_nest_start_noflag(skb, TCA_GRED_VQ_LIST); if (!vqs) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; struct nlattr *vq; if (!q) continue; vq = nla_nest_start_noflag(skb, TCA_GRED_VQ_ENTRY); if (!vq) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_FLAGS, q->red_flags)) goto nla_put_failure; /* Stats */ if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin, TCA_GRED_VQ_PAD)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PACKETS, q->packetsin)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_BACKLOG, gred_backlog(table, q, sch))) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_DROP, q->stats.prob_drop)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_MARK, q->stats.prob_mark)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_DROP, q->stats.forced_drop)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_MARK, q->stats.forced_mark)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PDROP, q->stats.pdrop)) goto nla_put_failure; nla_nest_end(skb, vq); } nla_nest_end(skb, vqs); return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static void gred_destroy(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); int i; for (i = 0; i < table->DPs; i++) gred_destroy_vq(table->tab[i]); if (table->opt) gred_offload(sch, TC_GRED_DESTROY); kfree(table->opt); } static struct Qdisc_ops gred_qdisc_ops __read_mostly = { .id = "gred", .priv_size = sizeof(struct gred_sched), .enqueue = gred_enqueue, .dequeue = gred_dequeue, .peek = qdisc_peek_head, .init = gred_init, .reset = gred_reset, .destroy = gred_destroy, .change = gred_change, .dump = gred_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("gred"); static int __init gred_module_init(void) { return register_qdisc(&gred_qdisc_ops); } static void __exit gred_module_exit(void) { unregister_qdisc(&gred_qdisc_ops); } module_init(gred_module_init) module_exit(gred_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic Random Early Detection qdisc"); |
| 11 11 11 11 4 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Public Key Signature Algorithm * * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/sig.h> #include <linux/cryptouser.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/string.h> #include <net/netlink.h> #include "internal.h" static void crypto_sig_exit_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); alg->exit(sig); } static int crypto_sig_init_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); if (alg->exit) sig->base.exit = crypto_sig_exit_tfm; if (alg->init) return alg->init(sig); return 0; } static void crypto_sig_free_instance(struct crypto_instance *inst) { struct sig_instance *sig = sig_instance(inst); sig->free(sig); } static void __maybe_unused crypto_sig_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : sig\n"); } static int __maybe_unused crypto_sig_report(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_sig rsig = {}; strscpy(rsig.type, "sig", sizeof(rsig.type)); return nla_put(skb, CRYPTOCFGA_REPORT_SIG, sizeof(rsig), &rsig); } static const struct crypto_type crypto_sig_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_sig_init_tfm, .free = crypto_sig_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_sig_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_sig_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SIG, .tfmsize = offsetof(struct crypto_sig, base), .algsize = offsetof(struct sig_alg, base), }; struct crypto_sig *crypto_alloc_sig(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_sig_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_sig); static int sig_default_sign(struct crypto_sig *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_verify(struct crypto_sig *tfm, const void *src, unsigned int slen, const void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_set_key(struct crypto_sig *tfm, const void *key, unsigned int keylen) { return -ENOSYS; } static unsigned int sig_default_size(struct crypto_sig *tfm) { return DIV_ROUND_UP_POW2(crypto_sig_keysize(tfm), BITS_PER_BYTE); } static int sig_prepare_alg(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; if (!alg->sign) alg->sign = sig_default_sign; if (!alg->verify) alg->verify = sig_default_verify; if (!alg->set_priv_key) alg->set_priv_key = sig_default_set_key; if (!alg->set_pub_key) return -EINVAL; if (!alg->key_size) return -EINVAL; if (!alg->max_size) alg->max_size = sig_default_size; if (!alg->digest_size) alg->digest_size = sig_default_size; base->cra_type = &crypto_sig_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_SIG; return 0; } int crypto_register_sig(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = sig_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_sig); void crypto_unregister_sig(struct sig_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_sig); int sig_register_instance(struct crypto_template *tmpl, struct sig_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = sig_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, sig_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(sig_register_instance); int crypto_grab_sig(struct crypto_sig_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_sig_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_sig); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Public Key Signature Algorithms"); |
| 612 611 10 6 708 390 52 4 443 441 443 710 707 710 702 10 1 700 23 3 703 3 549 199 703 1 314 161 1 128 1 103 220 214 4 3 395 1 29 1 1 125 1 168 1 1 4 582 131 25 106 90 261 372 712 313 3 311 148 1 146 293 146 10 10 10 156 327 708 709 168 444 121 10 177 1 705 702 419 419 372 374 5357 5356 10 10 684 2 684 617 117 12 449 85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> #include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. * @addr: The address to check * @len: The size of increase. * * Return: 0 on success. */ static int check_brk_limits(unsigned long addr, unsigned long len) { unsigned long mapped_addr; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; return mlock_future_ok(current->mm, current->mm->def_flags, len) ? 0 : -EAGAIN; } SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *brkvma, *next = NULL; unsigned long min_brk; bool populate = false; LIST_HEAD(uf); struct vma_iterator vmi; if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* Always allow shrinking brk. */ if (brk <= mm->brk) { /* Search one past newbrk */ vma_iter_init(&vmi, mm, newbrk); brkvma = vma_find(&vmi, oldbrk); if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. * do_vmi_align_munmap() will drop the lock on success, so * update it before calling do_vma_munmap(). */ mm->brk = brk; if (do_vmi_align_munmap(&vmi, brkvma, mm, newbrk, oldbrk, &uf, /* unlock = */ true)) goto out; goto success_unlocked; } if (check_brk_limits(oldbrk, newbrk - oldbrk)) goto out; /* * Only check if the next VMA is within the stack_guard_gap of the * expansion area */ vma_iter_init(&vmi, mm, oldbrk); next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; brkvma = vma_prev_limit(&vmi, mm->start_brk); /* Ok, looks good - let it rip. */ if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0) goto out; mm->brk = brk; if (mm->def_flags & VM_LOCKED) populate = true; success: mmap_write_unlock(mm); success_unlocked: userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: mm->brk = origbrk; mmap_write_unlock(mm); return origbrk; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes) { unsigned long locked_pages, limit_pages; if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) return true; locked_pages = bytes >> PAGE_SHIFT; locked_pages += mm->locked_vm; limit_pages = rlimit(RLIMIT_MEMLOCK); limit_pages >>= PAGE_SHIFT; return locked_pages <= limit_pages; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /** * do_mmap() - Perform a userland memory mapping into the current process * address space of length @len with protection bits @prot, mmap flags @flags * (from which VMA flags will be inferred), and any additional VMA flags to * apply @vm_flags. If this is a file-backed mapping then the file is specified * in @file and page offset into the file via @pgoff. * * This function does not perform security checks on the file and assumes, if * @uf is non-NULL, the caller has provided a list head to track unmap events * for userfaultfd @uf. * * It also simply indicates whether memory population is required by setting * @populate, which must be non-NULL, expecting the caller to actually perform * this task itself if appropriate. * * This function will invoke architecture-specific (and if provided and * relevant, file system-specific) logic to determine the most appropriate * unmapped area in which to place the mapping if not MAP_FIXED. * * Callers which require userland mmap() behaviour should invoke vm_mmap(), * which is also exported for module use. * * Those which require this behaviour less security checks, userfaultfd and * populate behaviour, and who handle the mmap write lock themselves, should * call this function. * * Note that the returned address may reside within a merged VMA if an * appropriate merge were to take place, so it doesn't necessarily specify the * start of a VMA, rather only the start of a valid mapped range of length * @len bytes, rounded down to the nearest page size. * * The caller must write-lock current->mm->mmap_lock. * * @file: An optional struct file pointer describing the file which is to be * mapped, if a file-backed mapping. * @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the * address at which to perform this mapping. See mmap (2) for details. Must be * page-aligned. * @len: The length of the mapping. Will be page-aligned and must be at least 1 * page in size. * @prot: Protection bits describing access required to the mapping. See mmap * (2) for details. * @flags: Flags specifying how the mapping should be performed, see mmap (2) * for details. * @vm_flags: VMA flags which should be set by default, or 0 otherwise. * @pgoff: Page offset into the @file if file-backed, should be 0 otherwise. * @populate: A pointer to a value which will be set to 0 if no population of * the range is required, or the number of bytes to populate if it is. Must be * non-NULL. See mmap (2) for details as to under what circumstances population * of the range occurs. * @uf: An optional pointer to a list head to track userfaultfd unmap events * should unmapping events arise. If provided, it is up to the caller to manage * this. * * Returns: Either an error, or the address at which the requested mapping has * been performed. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; int pkey = 0; *populate = 0; mmap_assert_write_locked(mm); if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we don't add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* * addr is returned from get_unmapped_area, * There are two cases: * 1> MAP_FIXED == false * unallocated memory, no need to check sealing. * 1> MAP_FIXED == true * sealing is checked inside mmap_region when * do_vmi_munmap is called. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (!mlock_future_ok(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; int err; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK; if (file->f_op->fop_flags & FOP_MMAP_SYNC) flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file_has_valid_mmap_hooks(file)) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } /* * Check to see if we are violating any seals and update VMA * flags if necessary to avoid future seal violations. */ err = memfd_check_seals_mmap(file, &vm_flags); if (err) return (unsigned long)err; } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_DROPPABLE: if (VM_DROPPABLE == VM_NONE) return -ENOTSUPP; /* * A locked or stack area makes no sense to be droppable. * * Also, since droppable pages can just go away at any time * it makes no sense to copy them on fork or dump them. * * And don't attempt to combine with hugetlb for now. */ if (flags & (MAP_LOCKED | MAP_HUGETLB)) return -EINVAL; if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP)) return -EINVAL; vm_flags |= VM_DROPPABLE; /* * If the pages can be dropped, then it doesn't make * sense to reserve them. */ vm_flags |= VM_NORESERVE; /* * Likewise, they're volatile enough that they * shouldn't survive forks or coredumps. */ vm_flags |= VM_WIPEONFORK | VM_DONTDUMP; fallthrough; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Determine if the allocation needs to ensure that there is no * existing mapping within it's guard gaps, for use as start_gap. */ static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) { if (vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.start_gap = stack_guard_placement(vm_flags); if (filp && is_file_hugepages(filp)) info.align_mask = huge_page_mask_align(filp); return vm_unmapped_area(&info); } #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.start_gap = stack_guard_placement(vm_flags); if (filp && is_file_hugepages(filp)) info.align_mask = huge_page_mask_align(filp); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags, vm_flags); } #endif unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags, vm_flags); return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); } unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. */ get_area = shmem_get_unmapped_area; } /* Always treat pgoff as zero for anonymous memory. */ if (!file) pgoff = 0; if (get_area) { addr = get_area(file, addr, len, pgoff, flags); } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); } else { addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len, pgoff, flags, vm_flags); } if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags, 0); return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL(mm_get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { unsigned long index = start_addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); /** * find_vma() - Find the VMA for a given address, or the next VMA. * @mm: The mm_struct to check * @addr: The address * * Returns: The VMA associated with addr, or the next VMA. * May return %NULL in the case of no VMA at addr or above. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { unsigned long index = addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); /** * find_vma_prev() - Find the VMA for a given address, or the next vma and * set %pprev to the previous VMA, if any. * @mm: The mm_struct to check * @addr: The address * @pprev: The pointer to set to the previous VMA * * Note that RCU lock is missing here since the external mmap_lock() is used * instead. * * Returns: The VMA associated with @addr, or the next vma. * May return %NULL in the case of no vma at addr or above. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, addr); vma = vma_iter_load(&vmi); *pprev = vma_prev(&vmi); if (!vma) vma = vma_next(&vmi); return vma; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; if (!prev) return NULL; if (expand_stack_locked(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; start = vma->vm_start; if (expand_stack_locked(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif #if defined(CONFIG_STACK_GROWSUP) #define vma_expand_up(vma,addr) expand_upwards(vma, addr) #define vma_expand_down(vma, addr) (-EFAULT) #else #define vma_expand_up(vma,addr) (-EFAULT) #define vma_expand_down(vma, addr) expand_downwards(vma, addr) #endif /* * expand_stack(): legacy interface for page faulting. Don't use unless * you have to. * * This is called with the mm locked for reading, drops the lock, takes * the lock for writing, tries to look up a vma again, expands it if * necessary, and downgrades the lock to reading again. * * If no vma is found or it can't be expanded, it returns NULL and has * dropped the lock. */ struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; mmap_read_unlock(mm); if (mmap_write_lock_killable(mm)) return NULL; vma = find_vma_prev(mm, addr, &prev); if (vma && vma->vm_start <= addr) goto success; if (prev && !vma_expand_up(prev, addr)) { vma = prev; goto success; } if (vma && !vma_expand_down(vma, addr)) goto success; mmap_write_unlock(mm); return NULL; success: mmap_write_downgrade(mm); return vma; } /* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls. * @mm: The mm_struct * @start: The start address to munmap * @len: The length to be munmapped. * @uf: The userfaultfd list_head * * Return: 0 on success, error otherwise. */ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { VMA_ITERATOR(vmi, mm, start); return do_vmi_munmap(&vmi, mm, start, len, uf, false); } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; vm_flags_t vm_flags; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_read_lock_killable(mm)) return -EINTR; /* * Look up VMA under read lock first so we can perform the security * without holding locks (which can be problematic). We reacquire a * write lock later and check nothing changed underneath us. */ vma = vma_lookup(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) { mmap_read_unlock(mm); return -EINVAL; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; /* Save vm_flags used to calculate prot and flags, and recheck later. */ vm_flags = vma->vm_flags; file = get_file(vma->vm_file); mmap_read_unlock(mm); /* Call outside mmap_lock to be consistent with other callers. */ ret = security_mmap_file(file, prot, flags); if (ret) { fput(file); return ret; } ret = -EINVAL; /* OK security check passed, take write lock + let it rip. */ if (mmap_write_lock_killable(mm)) { fput(file); return -EINTR; } vma = vma_lookup(mm, start); if (!vma) goto out; /* Make sure things didn't change under us. */ if (vma->vm_flags != vm_flags) goto out; if (vma->vm_file != file) goto out; if (start + size > vma->vm_end) { VMA_ITERATOR(vmi, mm, vma->vm_end); struct vm_area_struct *next, *prev = vma; for_each_vma_range(vmi, next, start + size) { /* hole between vmas ? */ if (next->vm_start != prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; prev = next; } if (!next) goto out; } ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); out: mmap_write_unlock(mm); fput(file); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; unsigned long len; int ret; bool populate; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, addr); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; ret = check_brk_limits(addr, len); if (ret) goto limits_failed; ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; vma = vma_prev(&vmi); ret = do_brk_flags(&vmi, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; munmap_failed: limits_failed: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(vm_brk_flags); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; VMA_ITERATOR(vmi, mm, 0); int count = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); mmap_read_lock(mm); arch_exit_mmap(mm); vma = vma_next(&vmi); if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); mmap_write_lock(mm); goto destroy; } flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX, false); mmap_read_unlock(mm); /* * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper * because the memory has been already freed. */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); vma_iter_set(&vmi, vma->vm_end); free_pgtables(&tlb, &vmi.mas, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); /* * Walk the list again, actually closing and freeing it, with preemption * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ vma_iter_set(&vmi, vma->vm_end); do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma_mark_detached(vma); remove_vma(vma); count++; cond_resched(); vma = vma_next(&vmi); } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); trace_exit_mmap(mm); destroy: __mt_destroy(&mm->mm_mt); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Close hook, called for unmap() and on the old vma for mremap(). * * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { const struct vm_special_mapping *sm = vma->vm_private_data; if (sm->close) sm->close(sm, vma); } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) { /* * Forbid splitting special mappings - kernel has expectations over * the number of pages in mapping. Together with VM_DONTEXPAND * the size of vma should stay the same over the special mapping's * lifetime. */ return -EINVAL; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, .may_split = special_mapping_split, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma_set_range(vma, addr, addr + len, 0); vm_flags_init(vma, (vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && vma->vm_ops == &special_mapping_vmops; } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } #ifdef CONFIG_SYSCTL #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) int sysctl_legacy_va_layout; #endif static const struct ctl_table mmap_table[] = { { .procname = "max_map_count", .data = &sysctl_max_map_count, .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) { .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS { .procname = "mmap_rnd_bits", .data = &mmap_rnd_bits, .maxlen = sizeof(mmap_rnd_bits), .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&mmap_rnd_bits_min, .extra2 = (void *)&mmap_rnd_bits_max, }, #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS { .procname = "mmap_rnd_compat_bits", .data = &mmap_rnd_compat_bits, .maxlen = sizeof(mmap_rnd_compat_bits), .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&mmap_rnd_compat_bits_min, .extra2 = (void *)&mmap_rnd_compat_bits_max, }, #endif }; #endif /* CONFIG_SYSCTL */ /* * initialise the percpu counter for VM, initialise VMA state. */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", mmap_table); #endif vma_state_init(); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (tmp > 0 && tmp < SZ_128K) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (tmp > 0 && tmp < SZ_8K) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static int __meminit init_reserve_notifier(void) { if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); /* * Obtain a read lock on mm->mmap_lock, if the specified address is below the * start of the VMA, the intent is to perform a write, and it is a * downward-growing stack, then attempt to expand the stack to contain it. * * This function is intended only for obtaining an argument page from an ELF * image, and is almost certainly NOT what you want to use for any other * purpose. * * IMPORTANT - VMA fields are accessed without an mmap lock being held, so the * VMA referenced must not be linked in any user-visible tree, i.e. it must be a * new VMA being mapped. * * The function assumes that addr is either contained within the VMA or below * it, and makes no attempt to validate this value beyond that. * * Returns true if the read lock was obtained and a stack was perhaps expanded, * false if the stack expansion failed. * * On stack expansion the function temporarily acquires an mmap write lock * before downgrading it. */ bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *new_vma, unsigned long addr, bool write) { if (!write || addr >= new_vma->vm_start) { mmap_read_lock(mm); return true; } if (!(new_vma->vm_flags & VM_GROWSDOWN)) return false; mmap_write_lock(mm); if (expand_downwards(new_vma, addr)) { mmap_write_unlock(mm); return false; } mmap_write_downgrade(mm); return true; } __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); if (mmap_write_lock_killable(oldmm)) return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } else { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ if (mpnt) { mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); /* Avoid OOM iterating a broken tree */ set_bit(MMF_OOM_SKIP, &mm->flags); } /* * The mm_struct is going to exit, but the locks will be dropped * first. Set the mm_struct as unstable is advisable as it is * not fully initialised. */ set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } |
| 205 11597 51 51 2 1740 1725 1657 1651 1653 1656 1660 1106 1109 626 148 83 148 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = false; rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ if (page_count_writable(page, u)) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) { return page_ref_add_unless(&folio->page, nr, u); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless(folio, 1, 0); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 34 34 146 146 20 20 20 17 3 20 20 20 20 45 45 44 45 45 45 20 23 10 23 5 20 45 45 45 45 1 56 55 1 6 50 32 22 3 29 8 23 23 22 23 26 4 22 15 10 1 5 5 150 1 154 7 95 38 1 36 37 585 586 80 395 586 7 75 461 156 58 362 419 360 67 38 420 407 378 5 1 4 5 1 1 1 40 40 4 37 26 15 2 24 25 1 1 6 5 1 6 4 21 21 21 21 24 2 22 15 10 1 1 5 5 579 582 538 538 76 393 82 75 430 129 406 406 265 268 408 1 1 1 1 33 33 17 146 146 146 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. * * Changes: * Paul `Rusty' Russell properly handle non-linear skbs * Harald Welte don't use nfcache */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/gue.h> #include <net/gre.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip6_route.h> #endif #include <net/ip_vs.h> #include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); EXPORT_SYMBOL(unregister_ip_vs_scheduler); EXPORT_SYMBOL(ip_vs_proto_name); EXPORT_SYMBOL(ip_vs_conn_new); EXPORT_SYMBOL(ip_vs_conn_in_get); EXPORT_SYMBOL(ip_vs_conn_out_get); #ifdef CONFIG_IP_VS_PROTO_TCP EXPORT_SYMBOL(ip_vs_tcp_conn_listen); #endif EXPORT_SYMBOL(ip_vs_conn_put); #ifdef CONFIG_IP_VS_DEBUG EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_TCP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) #else #define SNAT_CALL(f, ...) f(__VA_ARGS__) #endif static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; switch (proto) { case IPPROTO_IP: return "IP"; case IPPROTO_UDP: return "UDP"; case IPPROTO_TCP: return "TCP"; case IPPROTO_SCTP: return "SCTP"; case IPPROTO_ICMP: return "ICMP"; #ifdef CONFIG_IP_VS_IPV6 case IPPROTO_ICMPV6: return "ICMPv6"; #endif default: sprintf(buf, "IP_%u", proto); return buf; } } void ip_vs_init_hash_table(struct list_head *table, int rows) { while (--rows >= 0) INIT_LIST_HEAD(&table[rows]); } static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.inpkts); u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.outpkts); u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; local_bh_disable(); s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); local_bh_enable(); } static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (likely(pd->pp->state_transition)) pd->pp->state_transition(cp, direction, skb, pd); } static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) return p->pe->fill_param(p, skb); return 0; } /* * IPVS persistent scheduling function * It creates a connection entry according to its template if exists, * or selects a server and creates a connection entry plus a template. * Locking: we are svc user (svc->refcnt), so we hold all dests too * Protocols supported: TCP, UDP */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, __be16 src_port, __be16 dst_port, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ const union nf_inet_addr *src_addr, *dst_addr; if (likely(!ip_vs_iph_inverse(iph))) { src_addr = &iph->saddr; dst_addr = &iph->daddr; } else { src_addr = &iph->daddr; dst_addr = &iph->saddr; } /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and * it uses control connection and data connections. For active FTP, * FTP server initialize data connection to the client, its source port * is often 20. For passive FTP, FTP server tells the clients the port * that it passively listens to, and the client issues the data * connection. In the tunneling or direct routing mode, the load * balancer is on the client-to-server half of connection, the port * number is unknown to the load balancer. So, a conn template like * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP * service, and a template like <caddr, 0, vaddr, vport, daddr, dport> * is created for other persistent services. */ { int protocol = iph->protocol; const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. * fwmark template: * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: * <protocol,caddr,0,vaddr,0,daddr,0> */ if (svc->fwmark) { protocol = IPPROTO_IP; vaddr = &fwmark; } } /* return *ignored = -1 so NF_DROP can be used */ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, vaddr, vport, ¶m) < 0) { *ignored = -1; return NULL; } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct, NULL)) { struct ip_vs_scheduler *sched; /* * No template found or the dest of the connection * template is not available. * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); *ignored = 0; return NULL; } if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template * This adds param.pe_data to the template, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); *ignored = -1; return NULL; } ct->timeout = svc->timeout; } else { /* set destination with the found template */ dest = ct->dest; kfree(param.pe_data); } dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); *ignored = -1; return NULL; } /* * Add its control */ ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); ip_vs_conn_stats(cp, svc); return cp; } /* * IPVS main scheduling function * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP * * Usage of *ignored * * 1 : protocol tried to schedule (eg. on SYN), found svc but the * svc/scheduler decides that this packet should be accepted with * NF_ACCEPT because it must not be scheduled. * * 0 : scheduler can not find destination, so try bypass or * return ICMP and then NF_DROP (ip_vs_leave). * * -1 : scheduler tried to schedule but fatal error occurred, eg. * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param * failure such as missing Call-ID, ENOMEM on skb_linearize * or pe_data. In this case we should return NF_DROP without * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; __be16 _ports[2], *pptr, cport, vport; const void *caddr, *vaddr; unsigned int flags; *ignored = 1; /* * IPv6 frags, only the first hit here. */ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!ip_vs_iph_inverse(iph))) { cport = pptr[0]; caddr = &iph->saddr; vport = pptr[1]; vaddr = &iph->daddr; } else { cport = pptr[1]; caddr = &iph->daddr; vport = pptr[0]; vaddr = &iph->saddr; } /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ if (cport == FTPDATA) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } /* * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing" " connection"); __ip_vs_conn_put(cp); return NULL; } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; /* * Non-persistent service */ if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " "check your ipvs configuration\n"); return NULL; } sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a connection entry. */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; return NULL; } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; } static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } /* * Pass or drop the packet. * Called by ip_vs_in, when the virtual service is available but * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; struct netns_ipvs *ipvs = svc->ipvs; struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); if (!cp) return NF_DROP; } /* statistics */ ip_vs_in_stats(cp, skb); /* set state */ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) atomic_inc(&cp->control->in_pkts); else atomic_inc(&cp->in_pkts); ip_vs_conn_put(cp); return ret; } /* * When the virtual ftp service is presented, packets destined * for other services on the VIP may get here (except services * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; if (unlikely(ip_vs_iph_icmp(iph))) return NF_DROP; /* * Notify the client that the destination is unreachable, and * release the socket buffer. * Since it is in IP layer, the TCP socket is not actually * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { if (!skb->dev) skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } #ifdef CONFIG_SYSCTL static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return ipvs->sysctl_snat_reroute; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return ipvs->sysctl_nat_icmp_send; } #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) { if (NF_INET_LOCAL_IN == hooknum) return IP_DEFRAG_VS_IN; if (NF_INET_FORWARD == hooknum) return IP_DEFRAG_VS_FWD; return IP_DEFRAG_VS_OUT; } static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); return err; } static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, unsigned int hooknum) { if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; } /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct iphdr *iph = ip_hdr(skb); unsigned int icmp_offset = iph->ihl*4; struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + icmp_offset); struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } /* the TCP/UDP/SCTP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || IPPROTO_SCTP == ciph->protocol) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->checksum = 0; icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int icmp_offset = 0; unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; struct ipv6hdr *ciph; unsigned short fragoffs; ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); offs = icmp_offset + sizeof(struct icmp6hdr); ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; ciph->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; ciph->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol)) { __be16 *ports = (void *)(skb_network_header(skb) + offs); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, skb->len - icmp_offset, IPPROTO_ICMPV6, 0); skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMPv6"); else IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMPv6"); } #endif /* Handle relevant response ICMP messages - forward to the right * destination host. */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl, unsigned int hooknum) { unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); else #endif ip_vs_nat_icmp(skb, pp, cp, 1); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: __ip_vs_conn_put(cp); return verdict; } /* * Handle ICMP messages in the inside-to-outside direction (outgoing). * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; unsigned int offset, ihl; union nf_inet_addr snet; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); if (!pp) return NF_ACCEPT; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (ipvsh->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif /* * Check if sctp chunc is ABORT chunk */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) return 1; return 0; } static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } static inline bool is_new_conn(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { switch (iph->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) return false; return th->syn; } case IPPROTO_SCTP: { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; return sch->type == SCTP_CID_INIT; } default: return false; } } static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, int conn_reuse_mode) { /* Controlled (FTP DATA or persistence)? */ if (cp->control) return false; switch (cp->protocol) { case IPPROTO_TCP: return (cp->state == IP_VS_TCP_S_TIME_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || ((conn_reuse_mode & 2) && (cp->state == IP_VS_TCP_S_FIN_WAIT) && (cp->flags & IP_VS_CONN_F_NOOUTPUT)); case IPPROTO_SCTP: return cp->state == IP_VS_SCTP_S_CLOSED; default: return false; } } /* Generic function to create new connections for outgoing RS packets * * Pre-requisites for successful connection creation: * 1) Virtual Service is NOT fwmark based: * In fwmark-VS actual vaddr and vport are unknown to IPVS * 2) Real Server and Virtual Service were NOT configured without port: * This is to allow match of different VS to the same RS ip-addr */ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct sk_buff *skb, const struct ip_vs_iphdr *iph, __be16 dport, __be16 cport) { struct ip_vs_conn_param param; struct ip_vs_conn *ct = NULL, *cp = NULL; const union nf_inet_addr *vaddr, *daddr, *caddr; union nf_inet_addr snet; __be16 vport; unsigned int flags; vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; caddr = &iph->daddr; /* check pre-requisites are satisfied */ if (svc->fwmark) return NULL; if (!vport || !dport) return NULL; /* for persistent service first create connection template */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) { /* apply netmask the same way ingress-side does */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &caddr->in6, (__force __u32)svc->netmask); else #endif snet.ip = caddr->ip & svc->netmask; /* fill params and create template if not existent */ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol, &snet, 0, vaddr, vport, ¶m) < 0) return NULL; ct = ip_vs_ct_in_get(¶m); /* check if template exists and points to the same dest */ if (!ct || !ip_vs_check_template(ct, dest)) { ct = ip_vs_conn_new(¶m, dest->af, daddr, dport, IP_VS_CONN_F_TEMPLATE, dest, 0); if (!ct) { kfree(param.pe_data); return NULL; } ct->timeout = svc->timeout; } else { kfree(param.pe_data); } } /* connection flags */ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* create connection */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, ¶m); cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0); if (!cp) { if (ct) ip_vs_conn_put(ct); return NULL; } if (ct) { ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); } ip_vs_conn_stats(cp, svc); /* return connection (will be used to handle outgoing packet) */ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); return cp; } /* Handle outgoing packets which are considered requests initiated by * real servers, so that subsequent responses from external client can be * routed to the right real server. * Used also for outgoing responses in OPS mode. * * Connection management is handled by persistent-engine specific callback. */ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum, struct netns_ipvs *ipvs, int af, struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_conn *cp = NULL; __be16 _ports[2], *pptr; if (hooknum == NF_INET_LOCAL_IN) return NULL; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NULL; dest = ip_vs_find_real_service(ipvs, af, iph->protocol, &iph->saddr, pptr[0]); if (dest) { struct ip_vs_service *svc; struct ip_vs_pe *pe; svc = rcu_dereference(dest->svc); if (svc) { pe = rcu_dereference(svc->pe); if (pe && pe->conn_out) cp = pe->conn_out(svc, dest, skb, iph, pptr[0], pptr[1]); } } return cp; } /* Handle response packets: rewrite addresses and send away... */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ if (pp->snat_handler && !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ipv6_hdr(skb)->saddr = cp->vaddr.in6; else #endif { ip_hdr(skb)->saddr = cp->vaddr.ip; ip_send_check(ip_hdr(skb)); } /* * nf_iterate does not expect change in the skb->dst->dev. * It looks like it is not fatal to enable this code for hooks * where our handlers are at the end of the chain list and * when all next handlers use skb->dst->dev and not outdev. * It will definitely route properly the inout NAT traffic * when multiple paths are used. */ /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); return NF_STOLEN; } /* * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int af = state->pf; struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } if (unlikely(!skb_dst(skb))) return NF_ACCEPT; if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { /* Currently only for UDP: * connection oriented protocols typically use * ephemeral ports for outgoing connections, so * related incoming responses would not match any VS */ if (pp->protocol == IPPROTO_UDP) { cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); } } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no * existing entry if it is not RST * packet or not TCP packet. */ if ((iph.protocol != IPPROTO_TCP && iph.protocol != IPPROTO_SCTP) || ((iph.protocol == IPPROTO_TCP && !is_tcp_reset(skb, iph.len)) || (iph.protocol == IPPROTO_SCTP && !is_sctp_abort(skb, iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } } } IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; if (!iph->fragoffs) { /* No (second) fragments need to enter here, as nf_defrag_ipv6 * replayed fragment zero will already have created the cp */ /* Schedule and create new connection entry into cpp */ if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } if (unlikely(!*cpp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); /* Fragment couldn't be mapped to a conn entry */ if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); *verdict = NF_ACCEPT; return 0; } return 1; } /* Check the UDP tunnel and return its header length */ static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct udphdr _udph, *udph; struct ip_vs_dest *dest; udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (!udph) goto unk; offset += sizeof(struct udphdr); dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { struct guehdr _gueh, *gueh; gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); if (!gueh) goto unk; if (gueh->control != 0 || gueh->version != 0) goto unk; /* Later we can support also IPPROTO_IPV6 */ if (gueh->proto_ctype != IPPROTO_IPIP) goto unk; *proto = gueh->proto_ctype; return sizeof(struct udphdr) + sizeof(struct guehdr) + (gueh->hlen << 2); } unk: return 0; } /* Check the GRE tunnel and return its header length */ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct gre_base_hdr _greh, *greh; struct ip_vs_dest *dest; greh = skb_header_pointer(skb, offset, sizeof(_greh), &_greh); if (!greh) goto unk; dest = ip_vs_find_tunnel(ipvs, af, daddr, 0); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { IP_TUNNEL_DECLARE_FLAGS(flags); __be16 type; /* Only support version 0 and C (csum) */ if ((greh->flags & ~GRE_CSUM) != 0) goto unk; type = greh->protocol; /* Later we can support also IPPROTO_IPV6 */ if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; gre_flags_to_tnl_flags(flags, greh->flags); return gre_calc_hlen(flags); } unk: return 0; } /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, * forward to the right destination host if relevant. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; if (cih->protocol == IPPROTO_IPIP) { struct ip_vs_dest *dest; if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; offset2 = offset + cih->ihl * 4; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "UDP"; } else { ulen = ipvs_gre_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "GRE"; } if (ulen > 0) { /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih && cih->version == 4 && cih->ihl >= 5 && iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) { int v; if (tunnel || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } verdict = NF_DROP; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); goto out; } if (tunnel) { __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP/UDP/GRE header */ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) goto ignore_tunnel; /* Prefer the resulting PMTU */ if (dest) { struct ip_vs_dest_dst *dest_dst; dest_dst = rcu_dereference(dest->dest_dst); if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } if (mtu > 68 + sizeof(struct iphdr)) mtu -= sizeof(struct iphdr); info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of * original request. */ if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); ignore_tunnel: consume_skb(skb); verdict = NF_STOLEN; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; bool new_cp = false; *related = 1; ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (iph->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Cannot handle fragmented embedded protocol */ if (ciph.fragoffs) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { verdict = NF_ACCEPT; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #endif /* * Check if it's for virtual services, look it up, * and send it on its way... */ static unsigned int ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; int af = state->pf; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; /* * Big tappo: * - remote client: only PACKET_HOST * - route: used for struct net when skb->dev is unset */ if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ sk = skb_to_full_sk(skb); if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } /* Protocol supported? */ pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we * skip it if we're ignoring tunneled packets */ if (sysctl_ignore_tunneled(ipvs)) skb->ipvs_property = 1; return NF_ACCEPT; } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (conn_reuse_mode && is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { /* Do not reschedule controlling connection * that uses conntrack while it is still * referenced by controlled connection(s). */ resched = !old_ct; } } if (resched) { if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } } /* Check the server status */ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } else { __ip_vs_conn_put(cp); return NF_DROP; } } if (unlikely(!cp)) { int v; if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); ret = NF_ACCEPT; } /* Increase its packet counter and check if it is needed * to be synchronized * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout * * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_inc_return(&cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, pkts); else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) /* increment is done inside ip_vs_sync_conn too */ atomic_inc(&cp->control->in_pkts); ip_vs_conn_put(cp); return ret; } /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent * cache cluster, TCP packets can be marked and routed to ip_vs_in, * but ICMP destined for 0.0.0.0/0 cannot not be easily marked and * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain * and send them to ip_vs_in_icmp. */ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); int r; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; if (state->pf == NFPROTO_IPV4) { if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; #ifdef CONFIG_IP_VS_IPV6 } else { struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); #endif } return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #ifdef CONFIG_IP_VS_IPV6 static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #endif int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; int ret = 0; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return -EINVAL; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (!(ipvs->hooks_afmask & afmask)) { ret = nf_register_net_hooks(ipvs->net, ops, count); if (ret >= 0) ipvs->hooks_afmask |= afmask; } return ret; } void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (ipvs->hooks_afmask & afmask) { nf_unregister_net_hooks(ipvs->net, ops, count); ipvs->hooks_afmask &= ~afmask; } } /* * Initialize IP Virtual Server netns mem. */ static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) return -ENOMEM; /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; return 0; /* * Error handling */ sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; } static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */ list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } } static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } } static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit_batch = __ip_vs_cleanup_batch, .id = &ip_vs_net_id, .size = sizeof(struct netns_ipvs), }; static struct pernet_operations ipvs_core_dev_ops = { .exit_batch = __ip_vs_dev_cleanup_batch, }; /* * Initialize IP Virtual Server */ static int __init ip_vs_init(void) { int ret; ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); goto exit; } ip_vs_protocol_init(); ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) goto cleanup_sub; ret = ip_vs_register_nl_ioctl(); if (ret < 0) { pr_err("can't register netlink/ioctl.\n"); goto cleanup_dev; } pr_info("ipvs loaded.\n"); return ret; cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); cleanup_conn: ip_vs_conn_cleanup(); cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); exit: return ret; } static void __exit ip_vs_cleanup(void) { ip_vs_unregister_nl_ioctl(); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); /* common rcu_barrier() used by: * - ip_vs_control_cleanup() */ rcu_barrier(); pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); module_exit(ip_vs_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Virtual Server"); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | // SPDX-License-Identifier: GPL-2.0-only /* * Handshake request lifetime events * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2023, Oracle and/or its affiliates. */ #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <kunit/visibility.h> #include <uapi/linux/handshake.h> #include "handshake.h" #include <trace/events/handshake.h> /* * We need both a handshake_req -> sock mapping, and a sock -> * handshake_req mapping. Both are one-to-one. * * To avoid adding another pointer field to struct sock, net/handshake * maintains a hash table, indexed by the memory address of @sock, to * find the struct handshake_req outstanding for that socket. The * reverse direction uses a simple pointer field in the handshake_req * struct. */ static struct rhashtable handshake_rhashtbl ____cacheline_aligned_in_smp; static const struct rhashtable_params handshake_rhash_params = { .key_len = sizeof_field(struct handshake_req, hr_sk), .key_offset = offsetof(struct handshake_req, hr_sk), .head_offset = offsetof(struct handshake_req, hr_rhash), .automatic_shrinking = true, }; int handshake_req_hash_init(void) { return rhashtable_init(&handshake_rhashtbl, &handshake_rhash_params); } void handshake_req_hash_destroy(void) { rhashtable_destroy(&handshake_rhashtbl); } struct handshake_req *handshake_req_hash_lookup(struct sock *sk) { return rhashtable_lookup_fast(&handshake_rhashtbl, &sk, handshake_rhash_params); } EXPORT_SYMBOL_IF_KUNIT(handshake_req_hash_lookup); static bool handshake_req_hash_add(struct handshake_req *req) { int ret; ret = rhashtable_lookup_insert_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); return ret == 0; } static void handshake_req_destroy(struct handshake_req *req) { if (req->hr_proto->hp_destroy) req->hr_proto->hp_destroy(req); rhashtable_remove_fast(&handshake_rhashtbl, &req->hr_rhash, handshake_rhash_params); kfree(req); } static void handshake_sk_destruct(struct sock *sk) { void (*sk_destruct)(struct sock *sk); struct handshake_req *req; req = handshake_req_hash_lookup(sk); if (!req) return; trace_handshake_destruct(sock_net(sk), req, sk); sk_destruct = req->hr_odestruct; handshake_req_destroy(req); if (sk_destruct) sk_destruct(sk); } /** * handshake_req_alloc - Allocate a handshake request * @proto: security protocol * @flags: memory allocation flags * * Returns an initialized handshake_req or NULL. */ struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto, gfp_t flags) { struct handshake_req *req; if (!proto) return NULL; if (proto->hp_handler_class <= HANDSHAKE_HANDLER_CLASS_NONE) return NULL; if (proto->hp_handler_class >= HANDSHAKE_HANDLER_CLASS_MAX) return NULL; if (!proto->hp_accept || !proto->hp_done) return NULL; req = kzalloc(struct_size(req, hr_priv, proto->hp_privsize), flags); if (!req) return NULL; INIT_LIST_HEAD(&req->hr_list); req->hr_proto = proto; return req; } EXPORT_SYMBOL(handshake_req_alloc); /** * handshake_req_private - Get per-handshake private data * @req: handshake arguments * */ void *handshake_req_private(struct handshake_req *req) { return (void *)&req->hr_priv; } EXPORT_SYMBOL(handshake_req_private); static bool __add_pending_locked(struct handshake_net *hn, struct handshake_req *req) { if (WARN_ON_ONCE(!list_empty(&req->hr_list))) return false; hn->hn_pending++; list_add_tail(&req->hr_list, &hn->hn_requests); return true; } static void __remove_pending_locked(struct handshake_net *hn, struct handshake_req *req) { hn->hn_pending--; list_del_init(&req->hr_list); } /* * Returns %true if the request was found on @net's pending list, * otherwise %false. * * If @req was on a pending list, it has not yet been accepted. */ static bool remove_pending(struct handshake_net *hn, struct handshake_req *req) { bool ret = false; spin_lock(&hn->hn_lock); if (!list_empty(&req->hr_list)) { __remove_pending_locked(hn, req); ret = true; } spin_unlock(&hn->hn_lock); return ret; } struct handshake_req *handshake_req_next(struct handshake_net *hn, int class) { struct handshake_req *req, *pos; req = NULL; spin_lock(&hn->hn_lock); list_for_each_entry(pos, &hn->hn_requests, hr_list) { if (pos->hr_proto->hp_handler_class != class) continue; __remove_pending_locked(hn, pos); req = pos; break; } spin_unlock(&hn->hn_lock); return req; } EXPORT_SYMBOL_IF_KUNIT(handshake_req_next); /** * handshake_req_submit - Submit a handshake request * @sock: open socket on which to perform the handshake * @req: handshake arguments * @flags: memory allocation flags * * Return values: * %0: Request queued * %-EINVAL: Invalid argument * %-EBUSY: A handshake is already under way for this socket * %-ESRCH: No handshake agent is available * %-EAGAIN: Too many pending handshake requests * %-ENOMEM: Failed to allocate memory * %-EMSGSIZE: Failed to construct notification message * %-EOPNOTSUPP: Handshake module not initialized * * A zero return value from handshake_req_submit() means that * exactly one subsequent completion callback is guaranteed. * * A negative return value from handshake_req_submit() means that * no completion callback will be done and that @req has been * destroyed. */ int handshake_req_submit(struct socket *sock, struct handshake_req *req, gfp_t flags) { struct handshake_net *hn; struct net *net; int ret; if (!sock || !req || !sock->file) { kfree(req); return -EINVAL; } req->hr_sk = sock->sk; if (!req->hr_sk) { kfree(req); return -EINVAL; } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); hn = handshake_pernet(net); if (!hn) goto out_err; ret = -EAGAIN; if (READ_ONCE(hn->hn_pending) >= hn->hn_pending_max) goto out_err; spin_lock(&hn->hn_lock); ret = -EOPNOTSUPP; if (test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags)) goto out_unlock; ret = -EBUSY; if (!handshake_req_hash_add(req)) goto out_unlock; if (!__add_pending_locked(hn, req)) goto out_unlock; spin_unlock(&hn->hn_lock); ret = handshake_genl_notify(net, req->hr_proto, flags); if (ret) { trace_handshake_notify_err(net, req, req->hr_sk, ret); if (remove_pending(hn, req)) goto out_err; } /* Prevent socket release while a handshake request is pending */ sock_hold(req->hr_sk); trace_handshake_submit(net, req, req->hr_sk); return 0; out_unlock: spin_unlock(&hn->hn_lock); out_err: trace_handshake_submit_err(net, req, req->hr_sk, ret); handshake_req_destroy(req); return ret; } EXPORT_SYMBOL(handshake_req_submit); void handshake_complete(struct handshake_req *req, unsigned int status, struct genl_info *info) { struct sock *sk = req->hr_sk; struct net *net = sock_net(sk); if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { trace_handshake_complete(net, req, sk, status); req->hr_proto->hp_done(req, status, info); /* Handshake request is no longer pending */ sock_put(sk); } } EXPORT_SYMBOL_IF_KUNIT(handshake_complete); /** * handshake_req_cancel - Cancel an in-progress handshake * @sk: socket on which there is an ongoing handshake * * Request cancellation races with request completion. To determine * who won, callers examine the return value from this function. * * Return values: * %true - Uncompleted handshake request was canceled * %false - Handshake request already completed or not found */ bool handshake_req_cancel(struct sock *sk) { struct handshake_req *req; struct handshake_net *hn; struct net *net; net = sock_net(sk); req = handshake_req_hash_lookup(sk); if (!req) { trace_handshake_cancel_none(net, req, sk); return false; } hn = handshake_pernet(net); if (hn && remove_pending(hn, req)) { /* Request hadn't been accepted */ goto out_true; } if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { /* Request already completed */ trace_handshake_cancel_busy(net, req, sk); return false; } out_true: trace_handshake_cancel(net, req, sk); /* Handshake request is no longer pending */ sock_put(sk); return true; } EXPORT_SYMBOL(handshake_req_cancel); |
| 80 80 80 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TRAPS_H #define _ASM_X86_TRAPS_H #include <linux/context_tracking_state.h> #include <linux/kprobes.h> #include <asm/debugreg.h> #include <asm/idtentry.h> #include <asm/siginfo.h> /* TRAP_TRACE, ... */ #include <asm/trap_pf.h> #ifdef CONFIG_X86_64 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif extern int ibt_selftest(void); extern int ibt_selftest_noendbr(void); #ifdef CONFIG_X86_F00F_BUG /* For handling the FOOF bug */ void handle_invalid_op(struct pt_regs *regs); #endif static inline int get_si_code(unsigned long condition) { if (condition & DR_STEP) return TRAP_TRACE; else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) return TRAP_HWBKPT; else return TRAP_BRKPT; } void math_emulate(struct math_emu_info *); bool fault_in_kernel_space(unsigned long address); #ifdef CONFIG_VMAP_STACK void __noreturn handle_stack_overflow(struct pt_regs *regs, unsigned long fault_address, struct stack_info *info); #endif static inline void cond_local_irq_enable(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } static inline void cond_local_irq_disable(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); } #endif /* _ASM_X86_TRAPS_H */ |
| 146 146 146 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/inode.c * * Copyright (C) 1992 Rick Sladkey * * nfs inode and superblock handling functions * * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some * experimental NFS changes. Modularisation taken straight from SYS5 fs. * * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. * J.S.Peatfield@damtp.cam.ac.uk * */ #include <linux/module.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/time.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/unistd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/metrics.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/inet.h> #include <linux/nfs_xdr.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/freezer.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include "nfs4_fs.h" #include "callback.h" #include "delegation.h" #include "iostat.h" #include "internal.h" #include "fscache.h" #include "pnfs.h" #include "nfs.h" #include "netns.h" #include "sysfs.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 /* Default is to see 64-bit inode numbers */ static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED; static int nfs_update_inode(struct inode *, struct nfs_fattr *); static struct kmem_cache * nfs_inode_cachep; static inline unsigned long nfs_fattr_to_ino_t(struct nfs_fattr *fattr) { return nfs_fileid_to_ino_t(fattr->fileid); } int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { if (unlikely(nfs_current_task_exiting())) return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid * * This function returns a 32-bit inode number if the boot parameter * nfs.enable_ino64 is zero. */ u64 nfs_compat_user_ino64(u64 fileid) { #ifdef CONFIG_COMPAT compat_ulong_t ino; #else unsigned long ino; #endif if (enable_ino64) return fileid; ino = fileid; if (sizeof(ino) < sizeof(fileid)) ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8; return ino; } int nfs_drop_inode(struct inode *inode) { return NFS_STALE(inode) || generic_drop_inode(inode); } EXPORT_SYMBOL_GPL(nfs_drop_inode); void nfs_clear_inode(struct inode *inode) { /* * The following should never happen... */ WARN_ON_ONCE(nfs_have_writebacks(inode)); WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files)); nfs_zap_acl_cache(inode); nfs_access_zap_cache(inode); nfs_fscache_clear_inode(inode); } EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } int nfs_sync_inode(struct inode *inode) { inode_dio_wait(inode); return nfs_wb_all(inode); } EXPORT_SYMBOL_GPL(nfs_sync_inode); /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk * @mapping: pointer to struct address_space */ int nfs_sync_mapping(struct address_space *mapping) { int ret = 0; if (mapping->nrpages != 0) { unmap_mapping_range(mapping, 0, 0, 0); ret = nfs_wb_all(mapping->host); } return ret; } static int nfs_attribute_timeout(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); } static bool nfs_check_cache_flags_invalid(struct inode *inode, unsigned long flags) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); return (cache_validity & flags) != 0; } bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) { if (nfs_check_cache_flags_invalid(inode, flags)) return true; return nfs_attribute_cache_expired(inode); } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); #ifdef CONFIG_NFS_V4_2 static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return nfsi->xattr_cache != NULL; } #else static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return false; } #endif void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) { if (!(flags & NFS_INO_REVAL_FORCED)) flags &= ~(NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode, 0); flags &= ~NFS_INO_REVAL_FORCED; flags |= nfsi->cache_validity; if (inode->i_mapping->nrpages == 0) flags &= ~NFS_INO_INVALID_DATA; /* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */ smp_store_release(&nfsi->cache_validity, flags); if (inode->i_mapping->nrpages == 0 || nfsi->cache_validity & NFS_INO_INVALID_DATA) { nfs_ooo_clear(nfsi); } trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); /* * Invalidate the local caches */ static void nfs_zap_caches_locked(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); int mode = inode->i_mode; nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) { spin_lock(&inode->i_lock); nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { if (mapping->nrpages != 0) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); spin_unlock(&inode->i_lock); } } void nfs_zap_acl_cache(struct inode *inode) { void (*clear_acl_cache)(struct inode *); clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache; if (clear_acl_cache != NULL) clear_acl_cache(inode); spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { if (nfs_have_delegated_atime(inode)) return; spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_invalidate_atime); /* * Invalidate, but do not unhash, the inode. * NB: must be called with inode->i_lock held! */ static void nfs_set_inode_stale_locked(struct inode *inode) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); nfs_zap_caches_locked(inode); trace_nfs_set_inode_stale(inode); } void nfs_set_inode_stale(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_inode_stale_locked(inode); spin_unlock(&inode->i_lock); } struct nfs_find_desc { struct nfs_fh *fh; struct nfs_fattr *fattr; }; /* * In NFSv3 we can have 64bit inode numbers. In order to support * this, and re-exported directories (also seen in NFSv2) * we are forced to allow 2 different inodes to have the same * i_ino. */ static int nfs_find_actor(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fh *fh = desc->fh; struct nfs_fattr *fattr = desc->fattr; if (NFS_FILEID(inode) != fattr->fileid) return 0; if (inode_wrong_type(inode, fattr->mode)) return 0; if (nfs_compare_fh(NFS_FH(inode), fh)) return 0; if (is_bad_inode(inode) || NFS_STALE(inode)) return 0; return 1; } static int nfs_init_locked(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); inode->i_mode = fattr->mode; nfs_copy_fh(NFS_FH(inode), desc->fh); return 0; } #ifdef CONFIG_NFS_V4_SECURITY_LABEL static void nfs_clear_label_invalid(struct inode *inode) { spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; spin_unlock(&inode->i_lock); } void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { int error; if (fattr->label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { error = security_inode_notifysecctx(inode, fattr->label->label, fattr->label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, (char *)fattr->label->label, fattr->label->len, error); nfs_clear_label_invalid(inode); } } struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { struct nfs4_label *label; if (!(server->caps & NFS_CAP_SECURITY_LABEL)) return NULL; label = kzalloc(sizeof(struct nfs4_label), flags); if (label == NULL) return ERR_PTR(-ENOMEM); label->label = kzalloc(NFS4_MAXLABELLEN, flags); if (label->label == NULL) { kfree(label); return ERR_PTR(-ENOMEM); } label->len = NFS4_MAXLABELLEN; return label; } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { } #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); /* Search for inode identified by fh, fileid and i_mode in inode cache. */ struct inode * nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr, }; struct inode *inode; unsigned long hash; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || !(fattr->valid & NFS_ATTR_FATTR_TYPE)) return NULL; hash = nfs_fattr_to_ino_t(fattr); inode = ilookup5(sb, hash, nfs_find_actor, &desc); dprintk("%s: returning %p\n", __func__, inode); return inode; } static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); mutex_init(&nfsi->commit_mutex); } static void nfs_inode_init_dir(struct nfs_inode *nfsi) { nfsi->cache_change_attribute = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); init_rwsem(&nfsi->rmdir_sem); } /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. */ struct inode * nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr }; struct inode *inode = ERR_PTR(-ENOENT); u64 fattr_supported = NFS_SB(sb)->fattr_valid; unsigned long hash; nfs_attr_check_mountpoint(sb, fattr); if (nfs_attr_use_mounted_on_fileid(fattr)) fattr->fileid = fattr->mounted_on_fileid; else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; hash = nfs_fattr_to_ino_t(fattr); inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc); if (inode == NULL) { inode = ERR_PTR(-ENOMEM); goto out_no_inode; } if (inode->i_state & I_NEW) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long now = jiffies; /* We set i_ino for the few things that still rely on it, * such as stat(2) */ inode->i_ino = hash; /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; nfsi->cache_validity = 0; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && (fattr_supported & NFS_ATTR_FATTR_MODE)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; nfs_inode_init_regular(nfsi); mapping_set_large_folios(inode->i_mapping); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; nfs_inode_init_dir(nfsi); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else inode->i_op = &nfs_mountpoint_inode_operations; inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; inode_nohighmem(inode); } else init_special_inode(inode, inode->i_mode, fattr->rdev); inode_set_atime(inode, 0, 0); inode_set_mtime(inode, 0, 0); inode_set_ctime(inode, 0, 0); inode_set_iversion_raw(inode, 0); inode->i_size = 0; clear_nlink(inode); inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; nfsi->write_io = 0; nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode_set_iversion_raw(inode, fattr->change_attr); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE); if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK); else set_nlink(inode, 1); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_setsecurity(inode, fattr); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; nfsi->access_cache = RB_ROOT; nfs_fscache_init_inode(inode); unlock_new_inode(inode); } else { int err = nfs_refresh_inode(inode, fattr); if (err < 0) { iput(inode); inode = ERR_PTR(err); goto out_no_inode; } } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), nfs_display_fhandle_hash(fh), atomic_read(&inode->i_count)); out: return inode; out_no_inode: dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); goto out; } EXPORT_SYMBOL_GPL(nfs_fhget); static void nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr) { unsigned long cache_validity = NFS_I(inode)->cache_validity; if (nfs_have_delegated_mtime(inode)) { if (!(cache_validity & NFS_INO_INVALID_CTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PRECTIME | NFS_ATTR_FATTR_CTIME); if (!(cache_validity & NFS_INO_INVALID_MTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_MTIME); if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } else if (nfs_have_delegated_atime(inode)) { if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } } static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr) { unsigned int cache_flags = 0; if (attr->ia_valid & ATTR_MTIME_SET) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); struct timespec64 now; int updated = 0; now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; inode_set_mtime_to_ts(inode, attr->ia_mtime); if (!timespec64_equal(&now, &mtime)) updated |= S_MTIME; inode_maybe_inc_iversion(inode, updated); cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; } if (attr->ia_valid & ATTR_ATIME_SET) { inode_set_atime_to_ts(inode, attr->ia_atime); cache_flags |= NFS_INO_INVALID_ATIME; } NFS_I(inode)->cache_validity &= ~cache_flags; } static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid) { enum file_time_flags time_flags = 0; unsigned int cache_flags = 0; if (ia_valid & ATTR_MTIME) { time_flags |= S_MTIME | S_CTIME; cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; } if (ia_valid & ATTR_ATIME) { time_flags |= S_ATIME; cache_flags |= NFS_INO_INVALID_ATIME; } inode_update_timestamps(inode, time_flags); NFS_I(inode)->cache_validity &= ~cache_flags; } void nfs_update_delegated_atime(struct inode *inode) { spin_lock(&inode->i_lock); if (nfs_have_delegated_atime(inode)) nfs_update_timestamps(inode, ATTR_ATIME); spin_unlock(&inode->i_lock); } void nfs_update_delegated_mtime_locked(struct inode *inode) { if (nfs_have_delegated_mtime(inode)) nfs_update_timestamps(inode, ATTR_MTIME); } void nfs_update_delegated_mtime(struct inode *inode) { spin_lock(&inode->i_lock); nfs_update_delegated_mtime_locked(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_update_delegated_mtime); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); /* skip mode change if it's just for clearing setuid/setgid */ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; if (attr->ia_size == i_size_read(inode)) attr->ia_valid &= ~ATTR_SIZE; } if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); if (attr->ia_valid & ATTR_MTIME_SET) { nfs_set_timestamps_to_ts(inode, attr); attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| ATTR_ATIME|ATTR_ATIME_SET); } else { nfs_update_timestamps(inode, attr->ia_valid); attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME); } spin_unlock(&inode->i_lock); } else if (nfs_have_delegated_atime(inode) && attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { if (attr->ia_valid & ATTR_ATIME_SET) { spin_lock(&inode->i_lock); nfs_set_timestamps_to_ts(inode, attr); spin_unlock(&inode->i_lock); attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); } else { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME; } } /* Optimization: if the end result is no change, don't RPC */ if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; trace_nfs_setattr_enter(inode); /* Write all dirty data */ if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { error = -ENOMEM; goto out; } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); if (error == 0) error = nfs_refresh_inode(inode, fattr); nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); return error; } EXPORT_SYMBOL_GPL(nfs_setattr); /** * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall * @inode: inode of the file used * @offset: file offset to start truncating * * This is a copy of the common vmtruncate, but with the locking * corrected to take into account the fact that NFS requires * inode->i_size to be updated under the inode->i_lock. * Note: must be called with inode->i_lock held! */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { int err; err = inode_newsize_ok(inode, offset); if (err) goto out; trace_nfs_size_truncate(inode, offset); i_size_write(inode, offset); /* Optimisation */ if (offset == 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(NFS_I(inode)); } NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; spin_unlock(&inode->i_lock); truncate_pagecache(inode, offset); nfs_update_delegated_mtime_locked(inode); spin_lock(&inode->i_lock); out: return err; } /** * nfs_setattr_update_inode - Update inode metadata after a setattr call. * @inode: pointer to struct inode * @attr: pointer to struct iattr * @fattr: pointer to struct nfs_fattr * * Note: we do this in the *proc.c in order to ensure that * it works for things like exclusive creates too. */ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *fattr) { /* Barrier: bump the attribute generation count. */ nfs_fattr_set_barrier(fattr); spin_lock(&inode->i_lock); NFS_I(inode)->attr_gencount = fattr->gencount; if ((attr->ia_valid & ATTR_SIZE) != 0) { if (!nfs_have_delegated_mtime(inode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); nfs_vmtruncate(inode, attr->ia_size); } if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME; if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; if (setattr_should_drop_sgid(&nop_mnt_idmap, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } if ((attr->ia_valid & ATTR_UID) != 0) inode->i_uid = attr->ia_uid; if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL); } if (attr->ia_valid & (ATTR_ATIME_SET|ATTR_ATIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (attr->ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (attr->ia_valid & (ATTR_MTIME_SET|ATTR_MTIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (attr->ia_valid & ATTR_MTIME_SET) inode_set_mtime_to_ts(inode, attr->ia_mtime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (fattr->valid) nfs_update_inode(inode, fattr); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); /* * Don't request help from readdirplus if the file is being written to, * or if attribute caching is turned off */ static bool nfs_getattr_readdirplus_enable(const struct inode *inode) { return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ; } static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_miss(d_inode(parent)); dput(parent); } } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_hit(d_inode(parent)); dput(parent); } } static u32 nfs_get_valid_attrmask(struct inode *inode) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); u32 reply_mask = STATX_INO | STATX_TYPE; if (!(cache_validity & NFS_INO_INVALID_ATIME)) reply_mask |= STATX_ATIME; if (!(cache_validity & NFS_INO_INVALID_CTIME)) reply_mask |= STATX_CTIME; if (!(cache_validity & NFS_INO_INVALID_MTIME)) reply_mask |= STATX_MTIME; if (!(cache_validity & NFS_INO_INVALID_SIZE)) reply_mask |= STATX_SIZE; if (!(cache_validity & NFS_INO_INVALID_NLINK)) reply_mask |= STATX_NLINK; if (!(cache_validity & NFS_INO_INVALID_MODE)) reply_mask |= STATX_MODE; if (!(cache_validity & NFS_INO_INVALID_OTHER)) reply_mask |= STATX_UID | STATX_GID; if (!(cache_validity & NFS_INO_INVALID_BLOCKS)) reply_mask |= STATX_BLOCKS; if (!(cache_validity & NFS_INO_INVALID_CHANGE)) reply_mask |= STATX_CHANGE_COOKIE; return reply_mask; } int nfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct nfs_server *server = NFS_SERVER(inode); unsigned long cache_validity; int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode); trace_nfs_getattr_enter(inode); request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID | STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME | STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_CHANGE_COOKIE; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } /* Flush out writes to the server in order to update c/mtime/version. */ if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_CHANGE_COOKIE)) && S_ISREG(inode->i_mode)) { if (nfs_have_delegated_mtime(inode)) filemap_fdatawrite(inode->i_mapping); else filemap_write_and_wait(inode->i_mapping); } /* * We may force a getattr if the user cares about atime. * * Note that we only have to check the vfsmount flags here: * - NFS always sets S_NOATIME by so checking it would give a * bogus result * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is * no point in checking those. */ if ((path->mnt->mnt_flags & MNT_NOATIME) || ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) request_mask &= ~STATX_ATIME; /* Is the user requesting attributes that might need revalidation? */ if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME| STATX_MTIME|STATX_UID|STATX_GID| STATX_SIZE|STATX_BLOCKS| STATX_CHANGE_COOKIE))) goto out_no_revalidate; /* Check whether the cached attributes are stale */ do_update |= force_sync || nfs_attribute_cache_expired(inode); cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); do_update |= cache_validity & NFS_INO_INVALID_CHANGE; if (request_mask & STATX_ATIME) do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & STATX_CTIME) do_update |= cache_validity & NFS_INO_INVALID_CTIME; if (request_mask & STATX_MTIME) do_update |= cache_validity & NFS_INO_INVALID_MTIME; if (request_mask & STATX_SIZE) do_update |= cache_validity & NFS_INO_INVALID_SIZE; if (request_mask & STATX_NLINK) do_update |= cache_validity & NFS_INO_INVALID_NLINK; if (request_mask & STATX_MODE) do_update |= cache_validity & NFS_INO_INVALID_MODE; if (request_mask & (STATX_UID | STATX_GID)) do_update |= cache_validity & NFS_INO_INVALID_OTHER; if (request_mask & STATX_BLOCKS) do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_miss(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; } else if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); stat->change_cookie = inode_peek_iversion_raw(inode); stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC; if (server->change_attr_type != NFS4_CHANGE_TYPE_IS_UNDEFINED) stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC; if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; out: trace_nfs_getattr_exit(inode, err); return err; } EXPORT_SYMBOL_GPL(nfs_getattr); static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) { refcount_set(&l_ctx->count, 1); l_ctx->lockowner = current->files; INIT_LIST_HEAD(&l_ctx->list); atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *pos; list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) { if (pos->lockowner != current->files) continue; if (refcount_inc_not_zero(&pos->count)) return pos; } return NULL; } struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *res, *new = NULL; struct inode *inode = d_inode(ctx->dentry); rcu_read_lock(); res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { new = kmalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { new->open_context = get_nfs_open_context(ctx); if (new->open_context) { list_add_tail_rcu(&new->list, &ctx->lock_context.list); res = new; new = NULL; } else res = ERR_PTR(-EBADF); } spin_unlock(&inode->i_lock); kfree(new); } return res; } EXPORT_SYMBOL_GPL(nfs_get_lock_context); void nfs_put_lock_context(struct nfs_lock_context *l_ctx) { struct nfs_open_context *ctx = l_ctx->open_context; struct inode *inode = d_inode(ctx->dentry); if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock)) return; list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); put_nfs_open_context(ctx); kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); /** * nfs_close_context - Common close_context() routine NFSv2/v3 * @ctx: pointer to context * @is_sync: is this a synchronous close * * Ensure that the attributes are up to date if we're mounted * with close-to-open semantics and we have cached data that will * need to be revalidated on open. */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) { struct nfs_inode *nfsi; struct inode *inode; if (!(ctx->mode & FMODE_WRITE)) return; if (!is_sync) return; inode = d_inode(ctx->dentry); if (nfs_have_read_or_write_delegation(inode)) return; nfsi = NFS_I(inode); if (inode->i_mapping->nrpages == 0) return; if (nfsi->cache_validity & NFS_INO_INVALID_DATA) return; if (!list_empty(&nfsi->open_files)) return; if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO) return; nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } EXPORT_SYMBOL_GPL(nfs_close_context); struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp) { struct nfs_open_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); ctx->dentry = dget(dentry); if (filp) ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); rcu_assign_pointer(ctx->ll_cred, NULL); ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; ctx->flock_owner = (fl_owner_t)filp; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; nfs_localio_file_init(&ctx->nfl); return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count)) return ctx; return NULL; } EXPORT_SYMBOL_GPL(get_nfs_open_context); static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { struct inode *inode = d_inode(ctx->dentry); struct super_block *sb = ctx->dentry->d_sb; if (!refcount_dec_and_test(&ctx->lock_context.count)) return; if (!list_empty(&ctx->list)) { spin_lock(&inode->i_lock); list_del_rcu(&ctx->list); spin_unlock(&inode->i_lock); } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); nfs_close_local_fh(&ctx->nfl); kfree_rcu(ctx, rcu_head); } void put_nfs_open_context(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 0); } EXPORT_SYMBOL_GPL(put_nfs_open_context); static void put_nfs_open_context_sync(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 1); } /* * Ensure that mmap has a recent RPC credential for use when writing out * shared pages */ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) { struct inode *inode = d_inode(ctx->dentry); struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); if (list_empty(&nfsi->open_files) && nfs_ooo_test(nfsi)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { filp->private_data = get_nfs_open_context(ctx); set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); if (list_empty(&ctx->list)) nfs_inode_attach_open_context(ctx); } EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics */ struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; rcu_read_lock(); list_for_each_entry_rcu(pos, &nfsi->open_files, list) { if (cred != NULL && cred_fscmp(pos->cred, cred) != 0) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags)) continue; ctx = get_nfs_open_context(pos); if (ctx) break; } rcu_read_unlock(); return ctx; } void nfs_file_clear_open_context(struct file *filp) { struct nfs_open_context *ctx = nfs_file_open_context(filp); if (ctx) { struct inode *inode = d_inode(ctx->dentry); clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); /* * We fatal error on write before. Try to writeback * every page again. */ if (ctx->error < 0) invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; put_nfs_open_context_sync(ctx); } } /* * These allocate and release file read/write context information. */ int nfs_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; ctx = alloc_nfs_open_context(file_dentry(filp), flags_to_mode(filp->f_flags), filp); if (IS_ERR(ctx)) return PTR_ERR(ctx); nfs_file_set_open_context(filp, ctx); put_nfs_open_context(ctx); nfs_fscache_open_file(inode, filp); return 0; } /* * This function is called whenever some part of NFS notices that * the cached attributes have to be refreshed. */ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); trace_nfs_revalidate_inode_enter(inode); if (is_bad_inode(inode)) goto out; if (NFS_STALE(inode)) goto out; /* pNFS: Attributes aren't updated until we layoutcommit */ if (S_ISREG(inode->i_mode)) { status = pnfs_sync_inode(inode, false); if (status) goto out; } status = -ENOMEM; fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); switch (status) { case -ETIMEDOUT: /* A soft timeout occurred. Use cached information? */ if (server->flags & NFS_MOUNT_SOFTREVAL) status = 0; break; case -ESTALE: if (!S_ISDIR(inode->i_mode)) nfs_set_inode_stale(inode); else nfs_zap_caches(inode); } goto out; } status = nfs_refresh_inode(inode, fattr); if (status) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); goto out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); nfs_setsecurity(inode, fattr); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); return status; } int nfs_attribute_cache_expired(struct inode *inode) { if (nfs_have_delegated_attributes(inode)) return 0; return nfs_attribute_timeout(inode); } /** * nfs_revalidate_inode - Revalidate the inode attributes * @inode: pointer to inode struct * @flags: cache flags to check * * Updates inode attribute information by retrieving the data from the server. */ int nfs_revalidate_inode(struct inode *inode, unsigned long flags) { if (!nfs_check_cache_invalid(inode, flags)) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(NFS_SERVER(inode), inode); } EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { int ret; nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); if (ret < 0) return ret; } ret = invalidate_inode_pages2(mapping); if (ret < 0) return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); return 0; } /** * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping * * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ int nfs_clear_invalid_mapping(struct address_space *mapping) { struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings * are respected. But, that leaves a race window where one revalidator * can clear the flag, and then another checks it before the mapping * gets invalidated. Fix that by serializing access to this part of * the function. * * At the same time, we need to allow other tasks to see whether we * might be in the middle of invalidating the pages, so we only set * the bit lock here if it looks like we're going to be doing that. */ for (;;) { ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (ret) goto out; smp_rmb(); /* pairs with smp_wmb() below */ if (test_bit(NFS_INO_INVALIDATING, bitlock)) continue; /* pairs with nfs_set_cache_invalid()'s smp_store_release() */ if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA)) goto out; /* Slow-path that double-checks with spinlock held */ spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock)) { spin_unlock(&inode->i_lock); continue; } if (nfsi->cache_validity & NFS_INO_INVALID_DATA) break; spin_unlock(&inode->i_lock); goto out; } set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(nfsi); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); trace_nfs_invalidate_mapping_exit(inode, ret); clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); smp_mb__after_atomic(); wake_up_bit(bitlock, NFS_INO_INVALIDATING); out: return ret; } bool nfs_mapping_need_revalidate_inode(struct inode *inode) { return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) || NFS_STALE(inode); } int nfs_revalidate_mapping_rcu(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; if (IS_SWAPFILE(inode)) goto out; if (nfs_mapping_need_revalidate_inode(inode)) { ret = -ECHILD; goto out; } spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock) || (nfsi->cache_validity & NFS_INO_INVALID_DATA)) ret = -ECHILD; spin_unlock(&inode->i_lock); out: return ret; } /** * nfs_revalidate_mapping - Revalidate the pagecache * @inode: pointer to host inode * @mapping: pointer to mapping */ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { /* swapfiles are not supposed to be shared. */ if (IS_SWAPFILE(inode)) return 0; if (nfs_mapping_need_revalidate_inode(inode)) { int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) return ret; } return nfs_clear_invalid_mapping(mapping); } static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; if (!S_ISREG(inode->i_mode)) return false; if (list_empty(&nfsi->open_files)) return false; return inode_is_open_for_write(inode); } static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) { return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi); } static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); else if (nfs_server_capable(inode, NFS_CAP_XATTR)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); } /* If we have atomic WCC data, we may update some attributes */ ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) && timespec64_equal(&ts, &fattr->pre_ctime)) { inode_set_ctime_to_ts(inode, fattr->ctime); } ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { inode_set_mtime_to_ts(inode, fattr->mtime); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && !nfs_have_writebacks(inode)) { trace_nfs_size_wcc(inode, fattr->size); i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } } /** * nfs_check_inode_attributes - verify consistency of the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Verifies the attribute cache. If we have just changed the attributes, * so that fattr carries weak cache consistency data, then it may * also update the ctime/mtime/change_attribute. */ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; struct timespec64 ts; if (nfs_have_delegated_attributes(inode)) return 0; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; return -ESTALE; } if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_CHANGE; ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); if (cur_size != new_isize) invalid |= NFS_INO_INVALID_SIZE; } } /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) invalid |= NFS_INO_INVALID_MODE; if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid)) invalid |= NFS_INO_INVALID_OTHER; if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid)) invalid |= NFS_INO_INVALID_OTHER; /* Has the link count changed? */ if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_NLINK; ts = inode_get_atime(inode); if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) nfs_set_cache_invalid(inode, invalid); nfsi->read_cache_jiffies = fattr->time_start; return 0; } static atomic_long_t nfs_attr_generation_counter; static unsigned long nfs_read_attr_generation_counter(void) { return atomic_long_read(&nfs_attr_generation_counter); } unsigned long nfs_inc_attr_generation_counter(void) { return atomic_long_inc_return(&nfs_attr_generation_counter); } EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter); void nfs_fattr_init(struct nfs_fattr *fattr) { fattr->valid = 0; fattr->time_start = jiffies; fattr->gencount = nfs_inc_attr_generation_counter(); fattr->owner_name = NULL; fattr->group_name = NULL; fattr->mdsthreshold = NULL; } EXPORT_SYMBOL_GPL(nfs_fattr_init); /** * nfs_fattr_set_barrier * @fattr: attributes * * Used to set a barrier after an attribute was updated. This * barrier ensures that older attributes from RPC calls that may * have raced with our update cannot clobber these new values. * Note that you are still responsible for ensuring that other * operations which change the attribute on the server do not * collide. */ void nfs_fattr_set_barrier(struct nfs_fattr *fattr) { fattr->gencount = nfs_inc_attr_generation_counter(); } struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; fattr = kmalloc(sizeof(*fattr), GFP_KERNEL); if (fattr != NULL) { nfs_fattr_init(fattr); fattr->label = NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) { struct nfs_fattr *fattr = nfs_alloc_fattr(); if (!fattr) return NULL; fattr->label = nfs4_label_alloc(server, GFP_KERNEL); if (IS_ERR(fattr->label)) { kfree(fattr); return NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label); struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; fh = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); if (fh != NULL) fh->size = 0; return fh; } EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); #ifdef NFS_DEBUG /* * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle * in the same way that wireshark does * * @fh: file handle * * For debugging only. */ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) { /* wireshark uses 32-bit AUTODIN crc and does a bitwise * not on the result */ return nfs_fhandle_hash(fh); } EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console * * @fh: file handle to display * @caption: display caption * * For debugging only. */ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { unsigned short i; if (fh == NULL || fh->size == 0) { printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh); return; } printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n", caption, fh, fh->size, _nfs_display_fhandle_hash(fh)); for (i = 0; i < fh->size; i += 16) { __be32 *pos = (__be32 *)&fh->data[i]; switch ((fh->size - i - 1) >> 2) { case 0: printk(KERN_DEFAULT " %08x\n", be32_to_cpup(pos)); break; case 1: printk(KERN_DEFAULT " %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1)); break; case 2: printk(KERN_DEFAULT " %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2)); break; default: printk(KERN_DEFAULT " %08x %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2), be32_to_cpup(pos + 3)); } } } EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** * nfs_inode_attrs_cmp_generic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * Note also the check for wraparound of 'attr_gencount' * * The function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. Otherwise it returns * the value '0'. */ static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr, const struct inode *inode) { unsigned long attr_gencount = NFS_I(inode)->attr_gencount; return (long)(fattr->gencount - attr_gencount) > 0 || (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0; } /** * nfs_inode_attrs_cmp_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '0' indicates no measurable change * A return value of '-1' means that the attributes in @inode are * more recent. */ static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode); if (diff > 0) return 1; return diff == 0 ? 0 : -1; } /** * nfs_inode_attrs_cmp_strict_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes strictly monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '-1' means that the attributes in @inode are * more recent or unchanged. */ static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { return nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1; } /** * nfs_inode_attrs_cmp - compare attributes * @fattr: attributes * @inode: pointer to inode * * This function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. It returns '-1' if * the attributes in @inode are more recent than the ones in @fattr, * and it returns 0 if not sure. */ static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr, const struct inode *inode) { if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0) return 1; switch (NFS_SERVER(inode)->change_attr_type) { case NFS4_CHANGE_TYPE_IS_UNDEFINED: break; case NFS4_CHANGE_TYPE_IS_TIME_METADATA: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_monotonic(fattr, inode); default: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode); } return 0; } /** * nfs_inode_finish_partial_attr_update - complete a previous inode update * @fattr: attributes * @inode: pointer to inode * * Returns '1' if the last attribute update left the inode cached * attributes in a partially unrevalidated state, and @fattr * matches the change attribute of that partial update. * Otherwise returns '0'. */ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, const struct inode *inode) { const unsigned long check_valid = NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_NLINK; unsigned long cache_validity = NFS_I(inode)->cache_validity; enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type; if (ctype != NFS4_CHANGE_TYPE_IS_UNDEFINED && !(cache_validity & NFS_INO_INVALID_CHANGE) && (cache_validity & check_valid) != 0 && (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0) return 1; return 0; } static void nfs_ooo_merge(struct nfs_inode *nfsi, u64 start, u64 end) { int i, cnt; if (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) /* No point merging anything */ return; if (!nfsi->ooo) { nfsi->ooo = kmalloc(sizeof(*nfsi->ooo), GFP_ATOMIC); if (!nfsi->ooo) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; return; } nfsi->ooo->cnt = 0; } /* add this range, merging if possible */ cnt = nfsi->ooo->cnt; for (i = 0; i < cnt; i++) { if (end == nfsi->ooo->gap[i].start) end = nfsi->ooo->gap[i].end; else if (start == nfsi->ooo->gap[i].end) start = nfsi->ooo->gap[i].start; else continue; /* Remove 'i' from table and loop to insert the new range */ cnt -= 1; nfsi->ooo->gap[i] = nfsi->ooo->gap[cnt]; i = -1; } if (start != end) { if (cnt >= ARRAY_SIZE(nfsi->ooo->gap)) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; kfree(nfsi->ooo); nfsi->ooo = NULL; return; } nfsi->ooo->gap[cnt].start = start; nfsi->ooo->gap[cnt].end = end; cnt += 1; } nfsi->ooo->cnt = cnt; } static void nfs_ooo_record(struct nfs_inode *nfsi, struct nfs_fattr *fattr) { /* This reply was out-of-order, so record in the * pre/post change id, possibly cancelling * gaps created when iversion was jumpped forward. */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) nfs_ooo_merge(nfsi, fattr->change_attr, fattr->pre_change_attr); } static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int ret = 0; trace_nfs_refresh_inode_enter(inode); if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode)) ret = nfs_update_inode(inode, fattr); else { nfs_ooo_record(NFS_I(inode), fattr); if (attr_cmp == 0) ret = nfs_check_inode_attributes(inode, fattr); } trace_nfs_refresh_inode_exit(inode, ret); return ret; } /** * nfs_refresh_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Check that an RPC call that returned attributes has not overlapped with * other recent updates of the inode metadata, then decide whether it is * safe to do a full update of the inode attributes, or whether just to * call nfs_check_inode_attributes. */ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; spin_lock(&inode->i_lock); status = nfs_refresh_inode_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr, unsigned int invalid) { if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; return nfs_refresh_inode_locked(inode, fattr); } /** * nfs_post_op_update_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. * * NB: if the server didn't return any post op attributes, this * function will force the retrieval of attributes before the next * NFS request. Thus it should be used only for operations that * are expected to change one or more attributes, to avoid * unnecessary NFS requests and trips through nfs_update_inode(). */ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_REVAL_FORCED); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int status; /* Don't do a WCC update if these attributes are already stale */ if (attr_cmp < 0) return 0; if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) { /* Record the pre/post change info before clearing PRECHANGE */ nfs_ooo_record(NFS_I(inode), fattr); fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PRESIZE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME); goto out_noforce; } if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { fattr->pre_change_attr = inode_peek_iversion_raw(inode); fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { fattr->pre_ctime = inode_get_ctime(inode); fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { fattr->pre_mtime = inode_get_mtime(inode); fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { fattr->pre_size = i_size_read(inode); fattr->valid |= NFS_ATTR_FATTR_PRESIZE; } out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_BLOCKS); return status; } /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); /* * Many nfs protocol calls return the new file attributes after * an operation. Here we update the inode to reflect the state * of the server's inode. * * This is a bit tricky because we have to make sure all dirty pages * have been sent off to the server before calling invalidate_inode_pages. * To make sure no other process adds more write requests while we try * our best to flush them, we make them sleep during the attribute refresh. * * A very similar scenario holds for the dir cache. */ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_isize, new_isize; u64 fattr_supported = server->fattr_valid; unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; bool have_writers = nfs_file_has_buffered_writers(nfsi); bool cache_revalidated = true; bool attr_changed = false; bool have_delegation; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; printk(KERN_ERR "NFS: server %s error: fileid changed\n" "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id, (long long)nfsi->fileid, (long long)fattr->fileid); goto out_err; } /* * Make sure the inode's type hasn't changed. */ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) { /* * Big trouble! The inode has become a different object. */ printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", __func__, inode->i_ino, inode->i_mode, fattr->mode); goto out_err; } /* Update the fsid? */ if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && !nfs_fsid_equal(&server->fsid, &fattr->fsid) && !IS_AUTOMOUNT(inode)) server->fsid = fattr->fsid; /* Save the delegation state before clearing cache_validity */ have_delegation = nfs_have_delegated_attributes(inode); /* * Update the read time so we don't revalidate too often. */ nfsi->read_cache_jiffies = fattr->time_start; /* Fix up any delegated attributes in the struct nfs_fattr */ nfs_fattr_fixup_delegated(inode, fattr); save_cache_validity = nfsi->cache_validity; nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); if (pnfs_layoutcommit_outstanding(inode)) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS); cache_revalidated = false; } /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { if (!have_writers && nfsi->ooo && nfsi->ooo->cnt == 1 && nfsi->ooo->gap[0].end == inode_peek_iversion_raw(inode)) { /* There is one remaining gap that hasn't been * merged into iversion - do that now. */ inode_set_iversion_raw(inode, nfsi->ooo->gap[0].start); kfree(nfsi->ooo); nfsi->ooo = NULL; } if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { /* Could it be a race with writeback? */ if (!(have_writers || have_delegation)) { invalid |= NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR; /* Force revalidate of all attributes */ save_cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); attr_changed = true; dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } else if (!have_delegation) { nfs_ooo_record(nfsi, fattr); nfs_ooo_merge(nfsi, inode_peek_iversion_raw(inode), fattr->change_attr); } inode_set_iversion_raw(inode, fattr->change_attr); } } else { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CHANGE; if (!have_delegation || (nfsi->cache_validity & NFS_INO_INVALID_CHANGE) != 0) cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MTIME; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CTIME; /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { new_isize = nfs_size_to_loff_t(fattr->size); cur_isize = i_size_read(inode); if (new_isize != cur_isize && !have_delegation) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { trace_nfs_size_update(inode, new_isize); i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_DATA; } } if (new_isize == 0 && !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED | NFS_ATTR_FATTR_BLOCKS_USED))) { fattr->du.nfs3.used = 0; fattr->valid |= NFS_ATTR_FATTR_SPACE_USED; } } else nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_SIZE; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATIME; if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { umode_t newmode = inode->i_mode & S_IFMT; newmode |= fattr->mode & S_IALLUGO; inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; } } else if (fattr_supported & NFS_ATTR_FATTR_MODE) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MODE; if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } } else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } } else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) set_nlink(inode, fattr->nlink); } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_NLINK; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { if (cache_revalidated) { if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { nfsi->attrtimeo <<= 1; if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0) nfsi->attr_gencount = fattr->gencount; } /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); return 0; out_err: /* * No need to worry about unhashing the dentry, as the * lookup validation will know that the inode is bad. * (But we fall through to invalidate the caches.) */ nfs_set_inode_stale_locked(inode); return -ESTALE; } struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; nfsi = alloc_inode_sb(sb, nfs_inode_cachep, GFP_KERNEL); if (!nfsi) return NULL; nfsi->flags = 0UL; nfsi->cache_validity = 0UL; nfsi->ooo = NULL; #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_2 nfsi->xattr_cache = NULL; #endif nfs_netfs_inode_init(nfsi); return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); void nfs_free_inode(struct inode *inode) { kfree(NFS_I(inode)->ooo); kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } EXPORT_SYMBOL_GPL(nfs_free_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { #if IS_ENABLED(CONFIG_NFS_V4) INIT_LIST_HEAD(&nfsi->open_states); nfsi->delegation = NULL; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; #endif } static void init_once(void *foo) { struct nfs_inode *nfsi = foo; inode_init_once(&nfsi->vfs_inode); INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); nfs4_init_once(nfsi); } static int __init nfs_init_inodecache(void) { nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void nfs_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(nfs_inode_cachep); } struct workqueue_struct *nfslocaliod_workqueue; struct workqueue_struct *nfsiod_workqueue; EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* * Destroy the nfsiod workqueues */ static void nfsiod_stop(void) { struct workqueue_struct *wq; wq = nfsiod_workqueue; if (wq != NULL) { nfsiod_workqueue = NULL; destroy_workqueue(wq); } #if IS_ENABLED(CONFIG_NFS_LOCALIO) wq = nfslocaliod_workqueue; if (wq != NULL) { nfslocaliod_workqueue = NULL; destroy_workqueue(wq); } #endif /* CONFIG_NFS_LOCALIO */ } /* * Start the nfsiod workqueues */ static int nfsiod_start(void) { dprintk("RPC: creating workqueue nfsiod\n"); nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (nfsiod_workqueue == NULL) return -ENOMEM; #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* * localio writes need to use a normal (non-memreclaim) workqueue. * When we start getting low on space, XFS goes and calls flush_work() on * a non-memreclaim work queue, which causes a priority inversion problem. */ dprintk("RPC: creating workqueue nfslocaliod\n"); nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0); if (unlikely(nfslocaliod_workqueue == NULL)) { nfsiod_stop(); return -ENOMEM; } #endif /* CONFIG_NFS_LOCALIO */ return 0; } unsigned int nfs_net_id; EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); int err; nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { err = -ENOMEM; goto err_proc_rpc; } err = nfs_fs_proc_net_init(net); if (err) goto err_proc_nfs; return 0; err_proc_nfs: rpc_proc_unregister(net, "nfs"); err_proc_rpc: nfs_clients_exit(net); return err; } static void nfs_net_exit(struct net *net) { rpc_proc_unregister(net, "nfs"); nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } static struct pernet_operations nfs_net_ops = { .init = nfs_net_init, .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), }; /* * Initialize NFS */ static int __init init_nfs_fs(void) { int err; err = nfs_sysfs_init(); if (err < 0) goto out10; err = register_pernet_subsys(&nfs_net_ops); if (err < 0) goto out9; err = nfsiod_start(); if (err) goto out7; err = nfs_fs_proc_init(); if (err) goto out6; err = nfs_init_nfspagecache(); if (err) goto out5; err = nfs_init_inodecache(); if (err) goto out4; err = nfs_init_readpagecache(); if (err) goto out3; err = nfs_init_writepagecache(); if (err) goto out2; err = nfs_init_directcache(); if (err) goto out1; err = register_nfs_fs(); if (err) goto out0; return 0; out0: nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); out2: nfs_destroy_readpagecache(); out3: nfs_destroy_inodecache(); out4: nfs_destroy_nfspagecache(); out5: nfs_fs_proc_exit(); out6: nfsiod_stop(); out7: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); out10: return err; } static void __exit exit_nfs_fs(void) { nfs_destroy_directcache(); nfs_destroy_writepagecache(); nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); unregister_pernet_subsys(&nfs_net_ops); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); nfs_sysfs_exit(); } /* Not quite true; I just maintain it */ MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_DESCRIPTION("NFS client support"); MODULE_LICENSE("GPL"); module_param(enable_ino64, bool, 0644); module_init(init_nfs_fs) module_exit(exit_nfs_fs) |
| 225 765 223 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_NS_H #define _LINUX_PID_NS_H #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> #include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/idr.h> /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 struct fs_pin; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) /* modes for vm.memfd_noexec sysctl */ #define MEMFD_NOEXEC_SCOPE_EXEC 0 /* MFD_EXEC implied if unset */ #define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 /* MFD_NOEXEC_SEAL implied if unset */ #define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 /* same as 1, except MFD_EXEC rejected */ #endif struct pid_namespace { struct idr idr; struct rcu_head rcu; unsigned int pid_allocated; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; int pid_max; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #if defined(CONFIG_MEMFD_CREATE) int memfd_noexec_scope; #endif #endif } __randomize_layout; extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) refcount_inc(&ns->ns.count); return ns; } #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { int scope = MEMFD_NOEXEC_SCOPE_EXEC; for (; ns; ns = ns->parent) scope = max(scope, READ_ONCE(ns->memfd_noexec_scope)); return scope; } #else static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { return 0; } #endif extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); #else /* !CONFIG_PID_NS */ #include <linux/err.h> static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { return ns; } static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { return 0; } static inline struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); return ns; } static inline void put_pid_ns(struct pid_namespace *ns) { } static inline void zap_pid_ns_processes(struct pid_namespace *ns) { BUG(); } static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); int register_pidns_sysctls(struct pid_namespace *pidns); void unregister_pidns_sysctls(struct pid_namespace *pidns); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { return task_active_pid_ns(tsk) == &init_pid_ns; } #endif /* _LINUX_PID_NS_H */ |
| 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions Copyright (C) 1992 Drew Eckhardt */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/types.h> #include <linux/blk_types.h> #include <linux/device.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/bio.h> #include <linux/gfp.h> #include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/blkzoned.h> #include <linux/sched.h> #include <linux/sbitmap.h> #include <linux/uuid.h> #include <linux/xarray.h> #include <linux/file.h> #include <linux/lockdep.h> struct module; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct blkcg_gq; struct blk_flush_queue; struct kiocb; struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; struct blk_crypto_profile; extern const struct device_type disk_type; extern const struct device_type part_type; extern const struct class block_class; /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 6 #define DISK_MAX_PARTS 256 #define DISK_NAME_LEN 32 #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. * EFI UUID is 36 characters. MSDOS UUID is 11 characters. */ #define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) struct partition_meta_info { char uuid[PARTITION_META_INFO_UUIDLTH]; u8 volname[PARTITION_META_INFO_VOLNAMELTH]; }; /** * DOC: genhd capability flags * * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to * removable media. When set, the device remains present even when media is not * inserted. Shall not be set for devices which are removed entirely when the * media is removed. * * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, * doesn't appear in sysfs, and can't be opened from userspace or using * blkdev_get*. Used for the underlying components of multipath devices. * * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not * scan for partitions from add_disk, and users can't add partitions manually. * */ enum { GENHD_FL_REMOVABLE = 1 << 0, GENHD_FL_HIDDEN = 1 << 1, GENHD_FL_NO_PART = 1 << 2, }; enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; enum { /* Poll even if events_poll_msecs is unset */ DISK_EVENT_FLAG_POLL = 1 << 0, /* Forward events to udev */ DISK_EVENT_FLAG_UEVENT = 1 << 1, /* Block event polling when open for exclusive write */ DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, }; struct disk_events; struct badblocks; enum blk_integrity_checksum { BLK_INTEGRITY_CSUM_NONE = 0, BLK_INTEGRITY_CSUM_IP = 1, BLK_INTEGRITY_CSUM_CRC = 2, BLK_INTEGRITY_CSUM_CRC64 = 3, } __packed ; struct blk_integrity { unsigned char flags; enum blk_integrity_checksum csum_type; unsigned char tuple_size; unsigned char pi_offset; unsigned char interval_exp; unsigned char tag_size; }; typedef unsigned int __bitwise blk_mode_t; /* open for reading */ #define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) /* open for writing */ #define BLK_OPEN_WRITE ((__force blk_mode_t)(1 << 1)) /* open exclusively (vs other exclusive openers */ #define BLK_OPEN_EXCL ((__force blk_mode_t)(1 << 2)) /* opened with O_NDELAY */ #define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) /* open for "writes" only for ioctls (specialy hack for floppy.c) */ #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) /* return partition scanning errors */ #define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* * major/first_minor/minors should not be set by any new driver, the * block core will take care of allocating them automatically. */ int major; int first_minor; int minors; char disk_name[DISK_NAME_LEN]; /* name of major driver */ unsigned short events; /* supported events */ unsigned short event_flags; /* flags related to event processing */ struct xarray part_tbl; struct block_device *part0; const struct block_device_operations *fops; struct request_queue *queue; void *private_data; struct bio_set bio_split; int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 #define GD_DEAD 2 #define GD_NATIVE_CAPACITY 3 #define GD_ADDED 4 #define GD_SUPPRESS_PART_SCAN 5 #define GD_OWNS_QUEUE 6 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ struct backing_dev_info *bdi; struct kobject queue_kobj; /* the queue/ directory */ struct kobject *slave_dir; #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED struct list_head slave_bdevs; #endif struct timer_rand_state *random; struct disk_events *ev; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information. Reads of this information must be * protected with blk_queue_enter() / blk_queue_exit(). Modifying this * information is only allowed while no requests are being processed. * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned int zone_capacity; unsigned int last_zone_capacity; unsigned long __rcu *conv_zones_bitmap; unsigned int zone_wplugs_hash_bits; atomic_t nr_zone_wplugs; spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) struct cdrom_device_info *cdi; #endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; u64 diskseq; blk_mode_t open_mode; /* * Independent sector access ranges. This is always NULL for * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; struct mutex rqos_state_mutex; /* rqos state change mutex */ }; /** * disk_openers - returns how many openers are there for a disk * @disk: disk to check * * This returns the number of openers for a disk. Note that this value is only * stable if disk->open_mutex is held. * * Note: Due to a quirk in the block layer open code, each open partition is * only counted once even if there are multiple openers. */ static inline unsigned int disk_openers(struct gendisk *disk) { return atomic_read(&disk->part0->bd_openers); } /** * disk_has_partscan - return %true if partition scanning is enabled on a disk * @disk: disk to check * * Returns %true if partitions scanning is enabled for @disk, or %false if * partition scanning is disabled either permanently or temporarily. */ static inline bool disk_has_partscan(struct gendisk *disk) { return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); } /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. */ #define dev_to_disk(device) \ (dev_to_bdev(device)->bd_disk) #define disk_to_dev(disk) \ (&((disk)->part0->bd_device)) #if IS_REACHABLE(CONFIG_CDROM) #define disk_to_cdi(disk) ((disk)->cdi) #else #define disk_to_cdi(disk) NULL #endif static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); } /* * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) * however we constrain this to what we can validate and test. */ #define BLK_MAX_BLOCK_SIZE SZ_64K /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } static inline bool blk_op_is_passthrough(blk_opf_t op) { op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } /* flags set by the driver in queue_limits.features */ typedef unsigned int __bitwise blk_features_t; /* supports a volatile write cache */ #define BLK_FEAT_WRITE_CACHE ((__force blk_features_t)(1u << 0)) /* supports passing on the FUA bit */ #define BLK_FEAT_FUA ((__force blk_features_t)(1u << 1)) /* rotational device (hard drive or floppy) */ #define BLK_FEAT_ROTATIONAL ((__force blk_features_t)(1u << 2)) /* contributes to the random number pool */ #define BLK_FEAT_ADD_RANDOM ((__force blk_features_t)(1u << 3)) /* do disk/partitions IO accounting */ #define BLK_FEAT_IO_STAT ((__force blk_features_t)(1u << 4)) /* don't modify data until writeback is done */ #define BLK_FEAT_STABLE_WRITES ((__force blk_features_t)(1u << 5)) /* always completes in submit context */ #define BLK_FEAT_SYNCHRONOUS ((__force blk_features_t)(1u << 6)) /* supports REQ_NOWAIT */ #define BLK_FEAT_NOWAIT ((__force blk_features_t)(1u << 7)) /* supports DAX */ #define BLK_FEAT_DAX ((__force blk_features_t)(1u << 8)) /* supports I/O polling */ #define BLK_FEAT_POLL ((__force blk_features_t)(1u << 9)) /* is a zoned device */ #define BLK_FEAT_ZONED ((__force blk_features_t)(1u << 10)) /* supports PCI(e) p2p requests */ #define BLK_FEAT_PCI_P2PDMA ((__force blk_features_t)(1u << 12)) /* skip this queue in blk_mq_(un)quiesce_tagset */ #define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) /* undocumented magic for bcache */ #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ ((__force blk_features_t)(1u << 15)) /* atomic writes enabled */ #define BLK_FEAT_ATOMIC_WRITES \ ((__force blk_features_t)(1u << 16)) /* * Flags automatically inherited when stacking limits. */ #define BLK_FEAT_INHERIT_MASK \ (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \ BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) /* internal flags in queue_limits.flags */ typedef unsigned int __bitwise blk_flags_t; /* do not send FLUSH/FUA commands despite advertising a write cache */ #define BLK_FLAG_WRITE_CACHE_DISABLED ((__force blk_flags_t)(1u << 0)) /* I/O topology is misaligned */ #define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) /* passthrough command IO accounting */ #define BLK_FLAG_IOSTATS_PASSTHROUGH ((__force blk_flags_t)(1u << 2)) struct queue_limits { blk_features_t features; blk_flags_t flags; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; unsigned int max_hw_sectors; unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_user_sectors; unsigned int max_segment_size; unsigned int min_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_hw_zone_append_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned int zone_write_granularity; /* atomic write limits */ unsigned int atomic_write_hw_max; unsigned int atomic_write_max_sectors; unsigned int atomic_write_hw_boundary; unsigned int atomic_write_boundary_sectors; unsigned int atomic_write_hw_unit_min; unsigned int atomic_write_unit_min; unsigned int atomic_write_hw_unit_max; unsigned int atomic_write_unit_max; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned short max_write_streams; unsigned int write_stream_granularity; unsigned int max_open_zones; unsigned int max_active_zones; /* * Drivers that set dma_alignment to less than 511 must be prepared to * handle individual bvec's that are not a multiple of a SECTOR_SIZE * due to possible offsets. */ unsigned int dma_alignment; unsigned int dma_pad_mask; struct blk_integrity integrity; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes * a range of contiguous sectors that can be accessed using device command * execution resources that are independent from the resources used for * other access ranges. This is typically found with single-LUN multi-actuator * HDDs where each access range is served by a different set of heads. * The set of independent ranges supported by the device is defined using * struct blk_independent_access_ranges. The independent ranges must not overlap * and must include all sectors within the disk capacity (no sector holes * allowed). * For a device with multiple ranges, requests targeting sectors in different * ranges can be executed in parallel. A request can straddle an access range * boundary. */ struct blk_independent_access_range { struct kobject kobj; sector_t sector; sector_t nr_sectors; }; struct blk_independent_access_ranges { struct kobject kobj; bool sysfs_registered; unsigned int nr_ia_ranges; struct blk_independent_access_range ia_range[]; }; struct request_queue { /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; struct elevator_queue *elevator; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; unsigned int rq_timeout; unsigned int queue_depth; refcount_t refs; /* hw dispatch queues */ unsigned int nr_hw_queues; struct xarray hctx_table; struct percpu_ref q_usage_counter; struct lock_class_key io_lock_cls_key; struct lockdep_map io_lockdep_map; struct lock_class_key q_lock_cls_key; struct lockdep_map q_lockdep_map; struct request *last_merge; spinlock_t queue_lock; int quiesce_depth; struct gendisk *disk; /* * mq queue kobject */ struct kobject *mq_kobj; struct queue_limits limits; #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; #endif /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; struct blk_queue_stats *stats; struct rq_qos *rq_qos; struct mutex rq_qos_mutex; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; struct kobject *crypto_kobject; #endif struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_tags; struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; struct mutex blkcg_mutex; #endif int node; spinlock_t requeue_lock; struct list_head requeue_list; struct delayed_work requeue_work; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head flush_list; /* * Protects against I/O scheduler switching, particularly when updating * q->elevator. Since the elevator update code path may also modify q-> * nr_requests and wbt latency, this lock also protects the sysfs attrs * nr_requests and wbt_lat_usec. Additionally the nr_hw_queues update * may modify hctx tags, reserved-tags and cpumask, so this lock also * helps protect the hctx sysfs/debugfs attrs. To ensure proper locking * order during an elevator or nr_hw_queue update, first freeze the * queue, then acquire ->elevator_lock. */ struct mutex elevator_lock; struct mutex sysfs_lock; /* * Protects queue limits and also sysfs attribute read_ahead_kb. */ struct mutex limits_lock; /* * for reusing dead hctx instance in case of updating * nr_hw_queues */ struct list_head unused_hctx_list; spinlock_t unused_hctx_lock; int mq_freeze_depth; #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; #ifdef CONFIG_LOCKDEP struct task_struct *mq_freeze_owner; int mq_freeze_owner_depth; /* * Records disk & queue state in current context, used in unfreeze * queue */ bool mq_freeze_disk_dead; bool mq_freeze_queue_dying; #endif wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; /* * Serializes all debugfs metadata operations using the above dentries. */ struct mutex debugfs_mutex; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ enum { QUEUE_FLAG_DYING, /* queue being torn down */ QUEUE_FLAG_NOMERGES, /* disable merge attempts */ QUEUE_FLAG_SAME_COMP, /* complete on same CPU-group */ QUEUE_FLAG_FAIL_IO, /* fake timeout */ QUEUE_FLAG_NOXMERGES, /* No extended merges */ QUEUE_FLAG_SAME_FORCE, /* force complete on same CPU */ QUEUE_FLAG_INIT_DONE, /* queue is initialized */ QUEUE_FLAG_STATS, /* track IO start and completion times */ QUEUE_FLAG_REGISTERED, /* queue has been registered to a disk */ QUEUE_FLAG_QUIESCED, /* queue has been quiesced */ QUEUE_FLAG_RQ_ALLOC_TIME, /* record rq->alloc_time_ns */ QUEUE_FLAG_HCTX_ACTIVE, /* at least one blk-mq hctx is active */ QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ QUEUE_FLAG_MAX }; #define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) (!((q)->limits.features & BLK_FEAT_ROTATIONAL)) #define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) #define blk_queue_passthrough_stat(q) \ ((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH) #define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) #define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) #else #define blk_queue_rq_alloc_time(q) false #endif #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) #define blk_queue_disable_wbt(q) \ test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags) #define blk_queue_no_elv_switch(q) \ test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } #ifdef CONFIG_PM static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return q->rpm_status; } #else static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return RPM_ACTIVE; } #endif static inline bool blk_queue_is_zoned(struct request_queue *q) { return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && (q->limits.features & BLK_FEAT_ZONED); } static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { if (!blk_queue_is_zoned(disk->queue)) return 0; return sector >> ilog2(disk->queue->limits.chunk_sectors); } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_open_zones; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_active_zones; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, struct fwnode_handle *fwnode); int __must_check device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline int __must_check add_disk(struct gendisk *disk) { return device_add_disk(NULL, disk, NULL); } void del_gendisk(struct gendisk *gp); void invalidate_disk(struct gendisk *disk); void set_disk_ro(struct gendisk *disk, bool read_only); void disk_uevent(struct gendisk *disk, enum kobject_action action); static inline u8 bdev_partno(const struct block_device *bdev) { return atomic_read(&bdev->__bd_flags) & BD_PARTNO; } static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag) { return atomic_read(&bdev->__bd_flags) & flag; } static inline void bdev_set_flag(struct block_device *bdev, unsigned flag) { atomic_or(flag, &bdev->__bd_flags); } static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag) { atomic_andnot(flag, &bdev->__bd_flags); } static inline bool get_disk_ro(struct gendisk *disk) { return bdev_test_flag(disk->part0, BD_READ_ONLY) || test_bit(GD_READ_ONLY, &disk->state); } static inline bool bdev_read_only(struct block_device *bdev) { return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk); } bool set_capacity_and_notify(struct gendisk *disk, sector_t size); void disk_force_media_change(struct gendisk *disk); void bdev_mark_dead(struct block_device *bdev, bool surprise); void add_disk_randomness(struct gendisk *disk) __latent_entropy; void rand_initialize_disk(struct gendisk *disk); static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_start_sect; } static inline sector_t bdev_nr_sectors(struct block_device *bdev) { return bdev->bd_nr_sectors; } static inline loff_t bdev_nr_bytes(struct block_device *bdev) { return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) { return bdev_nr_sectors(disk->part0); } static inline u64 sb_bdev_nr_blocks(struct super_block *sb) { return bdev_nr_sectors(sb->s_bdev) >> (sb->s_blocksize_bits - SECTOR_SHIFT); } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int disk_nr_zones(struct gendisk *disk) { return disk->nr_zones; } bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); /** * disk_zone_capacity - returns the zone capacity of zone containing @sector * @disk: disk to work with * @sector: sector number within the querying zone * * Returns the zone capacity of a zone containing @sector. @sector can be any * sector in the zone. */ static inline unsigned int disk_zone_capacity(struct gendisk *disk, sector_t sector) { sector_t zone_sectors = disk->queue->limits.chunk_sectors; if (sector + zone_sectors >= get_capacity(disk)) return disk->last_zone_capacity; return disk->zone_capacity; } static inline unsigned int bdev_zone_capacity(struct block_device *bdev, sector_t pos) { return disk_zone_capacity(bdev->bd_disk, pos); } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; } static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { return false; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return disk_nr_zones(bdev->bd_disk); } int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node, struct lock_class_key *lkclass); /** * blk_alloc_disk - allocate a gendisk structure * @lim: queue limits to be used for this disk. * @node_id: numa node to allocate on * * Allocate and pre-initialize a gendisk structure for use with BIO based * drivers. * * Returns an ERR_PTR on error, else the allocated disk. * * Context: can sleep */ #define blk_alloc_disk(lim, node_id) \ ({ \ static struct lock_class_key __key; \ \ __blk_alloc_disk(lim, node_id, &__key); \ }) int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); bool disk_check_media_change(struct gendisk *disk); void set_capacity(struct gendisk *disk, sector_t size); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } #endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); struct bio *bio_split_to_limits(struct bio *bio); extern int blk_lld_busy(struct request_queue *q); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(enum req_op op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); const char *blk_status_to_str(blk_status_t status); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_queue; /* this is never NULL */ } /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int bio_zone_no(struct bio *bio) { return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } static inline bool bio_straddles_zones(struct bio *bio) { return bio_sectors(bio) && bio_zone_no(bio) != disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* * Return how much within the boundary is left to be used for I/O at a given * offset. */ static inline unsigned int blk_boundary_sectors_left(sector_t offset, unsigned int boundary_sectors) { if (unlikely(!is_power_of_2(boundary_sectors))) return boundary_sectors - sector_div(offset, boundary_sectors); return boundary_sectors - (offset & (boundary_sectors - 1)); } /** * queue_limits_start_update - start an atomic update of queue limits * @q: queue to update * * This functions starts an atomic update of the queue limits. It takes a lock * to prevent other updates and returns a snapshot of the current limits that * the caller can modify. The caller must call queue_limits_commit_update() * to finish the update. * * Context: process context. */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) { mutex_lock(&q->limits_lock); return q->limits; } int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim); int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); int blk_validate_limits(struct queue_limits *lim); /** * queue_limits_cancel_update - cancel an atomic update of queue limits * @q: queue to update * * This functions cancels an atomic update of the queue limits started by * queue_limits_start_update() and should be used when an error occurs after * starting update. */ static inline void queue_limits_cancel_update(struct request_queue *q) { mutex_unlock(&q->limits_lock); } /* * These helpers are for drivers that have sloppy feature negotiation and might * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O * completion handler when the device returned an indicator that the respective * feature is not actually supported. They are racy and the driver needs to * cope with that. Try to avoid this scheme if you can. */ static inline void blk_queue_disable_discard(struct request_queue *q) { q->limits.max_discard_sectors = 0; } static inline void blk_queue_disable_secure_erase(struct request_queue *q) { q->limits.max_secure_erase_sectors = 0; } static inline void blk_queue_disable_write_zeroes(struct request_queue *q) { q->limits.max_write_zeroes_sectors = 0; } /* * Access functions for manipulating queue properties */ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); struct blk_independent_access_ranges * disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); void blk_mark_disk_dead(struct gendisk *disk); struct rq_list { struct request *head; struct request *tail; }; #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to * the device's request_queue in a batch, this results in improved scalability * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list * or when attempting a merge. For details, please see schedule() where * blk_flush_plug() is called. */ struct blk_plug { struct rq_list mq_list; /* blk-mq requests */ /* if ios_left is > 1, we can batch tag/rq allocations */ struct rq_list cached_rqs; u64 cur_ktime; unsigned short nr_ios; unsigned short rq_count; bool multiple_queues; bool has_elevator; struct list_head cb_list; /* md requires an unplug callback */ }; struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; void *data; }; extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); void __blk_flush_plug(struct blk_plug *plug, bool from_schedule); static inline void blk_flush_plug(struct blk_plug *plug, bool async) { if (plug) __blk_flush_plug(plug, async); } /* * tsk == current here */ static inline void blk_plug_invalidate_ts(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS; } int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { }; static inline void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) { } static inline void blk_start_plug(struct blk_plug *plug) { } static inline void blk_finish_plug(struct blk_plug *plug) { } static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } static inline void blk_plug_invalidate_ts(struct task_struct *tsk) { } static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; } static inline long nr_blockdev_pages(void) { return 0; } #endif /* CONFIG_BLOCK */ extern void blk_io_schedule(void); int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ #define BLKDEV_ZERO_KILLABLE (1 << 2) /* interruptible by fatal signals */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) { return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, 0); } static inline bool bdev_is_partition(struct block_device *bdev) { return bdev_partno(bdev) != 0; } enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; /* * Default upper limit for the software max_sectors limit used for * regular file system I/O. This can be increased through sysfs. * * Not to be confused with the max_hw_sector limit that is entirely * controlled by the driver, usually based on hardware limits. */ #define BLK_DEF_MAX_SECTORS_CAP 2560u static inline struct queue_limits *bdev_limits(struct block_device *bdev) { return &bdev_get_queue(bdev)->limits; } static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; } static inline unsigned long queue_virt_boundary(const struct request_queue *q) { return q->limits.virt_boundary_mask; } static inline unsigned int queue_max_sectors(const struct request_queue *q) { return q->limits.max_sectors; } static inline unsigned int queue_max_bytes(struct request_queue *q) { return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9; } static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; } static inline unsigned short queue_max_segments(const struct request_queue *q) { return q->limits.max_segments; } static inline unsigned short queue_max_discard_segments(const struct request_queue *q) { return q->limits.max_discard_segments; } static inline unsigned int queue_max_segment_size(const struct request_queue *q) { return q->limits.max_segment_size; } static inline bool queue_emulates_zone_append(struct request_queue *q) { return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors; } static inline bool bdev_emulates_zone_append(struct block_device *bdev) { return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int bdev_max_zone_append_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_zone_append_sectors; } static inline unsigned int bdev_max_segments(struct block_device *bdev) { return queue_max_segments(bdev_get_queue(bdev)); } static inline unsigned short bdev_max_write_streams(struct block_device *bdev) { if (bdev_is_partition(bdev)) return 0; return bdev_limits(bdev)->max_write_streams; } static inline unsigned queue_logical_block_size(const struct request_queue *q) { return q->limits.logical_block_size; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_physical_block_size(const struct request_queue *q) { return q->limits.physical_block_size; } static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_io_min(const struct request_queue *q) { return q->limits.io_min; } static inline unsigned int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } static inline unsigned int queue_io_opt(const struct request_queue *q) { return q->limits.io_opt; } static inline unsigned int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline unsigned int queue_zone_write_granularity(const struct request_queue *q) { return q->limits.zone_write_granularity; } static inline unsigned int bdev_zone_write_granularity(struct block_device *bdev) { return queue_zone_write_granularity(bdev_get_queue(bdev)); } int bdev_alignment_offset(struct block_device *bdev); unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_discard_sectors; } static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { return bdev_limits(bdev)->discard_granularity; } static inline unsigned int bdev_max_secure_erase_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_secure_erase_sectors; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) { return blk_queue_nonrot(bdev_get_queue(bdev)); } static inline bool bdev_synchronous(struct block_device *bdev) { return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS; } static inline bool bdev_stable_writes(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE) return true; return q->limits.features & BLK_FEAT_STABLE_WRITES; } static inline bool blk_queue_write_cache(struct request_queue *q) { return (q->limits.features & BLK_FEAT_WRITE_CACHE) && !(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED); } static inline bool bdev_write_cache(struct block_device *bdev) { return blk_queue_write_cache(bdev_get_queue(bdev)); } static inline bool bdev_fua(struct block_device *bdev) { return bdev_limits(bdev)->features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) { return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT; } static inline bool bdev_is_zoned(struct block_device *bdev) { return blk_queue_is_zoned(bdev_get_queue(bdev)); } static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) { return disk_zone_no(bdev->bd_disk, sec); } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (!blk_queue_is_zoned(q)) return 0; return q->limits.chunk_sectors; } static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, sector_t sector) { return sector & (bdev_zone_sectors(bdev) - 1); } static inline sector_t bio_offset_from_zone_start(struct bio *bio) { return bdev_offset_from_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector); } static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { return bdev_offset_from_zone_start(bdev, sector) == 0; } /* Check whether @sector is a multiple of the zone size. */ static inline bool bdev_is_zone_aligned(struct block_device *bdev, sector_t sector) { return bdev_is_zone_start(bdev, sector); } /** * bdev_zone_is_seq - check if a sector belongs to a sequential write zone * @bdev: block device to check * @sector: sector number * * Check if @sector on @bdev is contained in a sequential write required zone. */ static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector) { bool is_seq = false; #if IS_ENABLED(CONFIG_BLK_DEV_ZONED) if (bdev_is_zoned(bdev)) { struct gendisk *disk = bdev->bd_disk; unsigned long *bitmap; rcu_read_lock(); bitmap = rcu_dereference(disk->conv_zones_bitmap); is_seq = !bitmap || !test_bit(disk_zone_no(disk, sector), bitmap); rcu_read_unlock(); } #endif return is_seq; } int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); static inline unsigned int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; } static inline unsigned int queue_atomic_write_unit_max_bytes(const struct request_queue *q) { return q->limits.atomic_write_unit_max; } static inline unsigned int queue_atomic_write_unit_min_bytes(const struct request_queue *q) { return q->limits.atomic_write_unit_min; } static inline unsigned int queue_atomic_write_boundary_bytes(const struct request_queue *q) { return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT; } static inline unsigned int queue_atomic_write_max_bytes(const struct request_queue *q) { return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) { return queue_dma_alignment(bdev_get_queue(bdev)); } static inline bool bdev_iter_is_aligned(struct block_device *bdev, struct iov_iter *iter) { return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev), bdev_logical_block_size(bdev) - 1); } static inline unsigned int blk_lim_dma_alignment_and_pad(struct queue_limits *lim) { return lim->dma_alignment | lim->dma_pad_mask; } static inline bool blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits); return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT; } int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q) { return true; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { /* these match the Designator Types specified in SPC */ BLK_UID_T10 = 1, BLK_UID_EUI64 = 2, BLK_UID_NAA = 3, }; struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int (*open)(struct gendisk *disk, blk_mode_t mode); void (*release)(struct gendisk *disk); int (*ioctl)(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg); int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); void (*free_disk)(struct gendisk *disk); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); char *(*devnode)(struct gendisk *disk, umode_t *mode); /* returns the length of the identifier or a negative errno: */ int (*get_unique_id)(struct gendisk *disk, u8 id[16], enum blk_unique_id id_type); struct module *owner; const struct pr_ops *pr_ops; /* * Special callback for probing GPT entry at a given sector. * Needed by Android devices, used by GPT scanner and MMC blk * driver. */ int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector); }; #ifdef CONFIG_COMPAT extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL #endif static inline void blk_wake_io_task(struct task_struct *waiter) { /* * If we're polling, the task itself is doing the completions. For * that case, we don't need to signal a wakeup, it's enough to just * mark us as RUNNING. */ if (waiter == current) __set_current_state(TASK_RUNNING); else wake_up_process(waiter); } unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for * @start_time: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } int bdev_validate_blocksize(struct block_device *bdev, int block_size); int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK #define BLKDEV_MAJOR_MAX 512 #else #define BLKDEV_MAJOR_MAX 0 #endif struct blk_holder_ops { void (*mark_dead)(struct block_device *bdev, bool surprise); /* * Sync the file system mounted on the block device. */ void (*sync)(struct block_device *bdev); /* * Freeze the file system mounted on the block device. */ int (*freeze)(struct block_device *bdev); /* * Thaw the file system mounted on the block device. */ int (*thaw)(struct block_device *bdev); }; /* * For filesystems using @fs_holder_ops, the @holder argument passed to * helpers used to open and claim block devices via * bd_prepare_to_claim() must point to a superblock. */ extern const struct blk_holder_ops fs_holder_ops; /* * Return the correct open flags for blkdev_get_by_* for super block flags * as stored in sb->s_flags. */ #define sb_open_mode(flags) \ (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \ (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); struct block_device *I_BDEV(struct inode *inode); struct block_device *file_bdev(struct file *bdev_file); bool disk_live(struct gendisk *disk); unsigned int block_size(struct block_device *bdev); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else static inline void invalidate_bdev(struct block_device *bdev) { } static inline int sync_blockdev(struct block_device *bdev) { return 0; } static inline int sync_blockdev_nowait(struct block_device *bdev) { return 0; } static inline void sync_bdevs(bool wait) { } static inline void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask) { } static inline void printk_all_partitions(void) { } static inline int early_lookup_bdev(const char *pathname, dev_t *dev) { return -EINVAL; } #endif /* CONFIG_BLOCK */ int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct rq_list req_list; bool need_ts; void (*complete)(struct io_comp_batch *); }; static inline bool blk_atomic_write_start_sect_aligned(sector_t sector, struct queue_limits *limits) { unsigned int alignment = max(limits->atomic_write_hw_unit_min, limits->atomic_write_hw_boundary); return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT); } static inline bool bdev_can_atomic_write(struct block_device *bdev) { struct request_queue *bd_queue = bdev->bd_queue; struct queue_limits *limits = &bd_queue->limits; if (!limits->atomic_write_unit_min) return false; if (bdev_is_partition(bdev)) return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect, limits); return true; } static inline unsigned int bdev_atomic_write_unit_min_bytes(struct block_device *bdev) { if (!bdev_can_atomic_write(bdev)) return 0; return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev)); } static inline unsigned int bdev_atomic_write_unit_max_bytes(struct block_device *bdev) { if (!bdev_can_atomic_write(bdev)) return 0; return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev)); } #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ |
| 113 640 724 721 643 724 718 716 717 716 153 1 146 1 148 153 150 3 155 146 157 157 156 1 6 5 4 3 6 6 146 146 8 8 8 28 1 1 2 2 2 2 12 6 7 7 2 3 5 1 1 8 1 7 2 2 2 2 1 9 2 2 2 4 1 18 18 11 2 9 2 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 | // SPDX-License-Identifier: GPL-2.0 /* * IPv6 Address Label subsystem * for the IPv6 "Default" Source Address Selection * * Copyright (C)2007 USAGI/WIDE Project */ /* * Author: * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> */ #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/in6.h> #include <linux/slab.h> #include <net/addrconf.h> #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> #if 0 #define ADDRLABEL(x...) printk(x) #else #define ADDRLABEL(x...) do { ; } while (0) #endif /* * Policy Table */ struct ip6addrlbl_entry { struct in6_addr prefix; int prefixlen; int ifindex; int addrtype; u32 label; struct hlist_node list; struct rcu_head rcu; }; /* * Default policy table (RFC6724 + extensions) * * prefix addr_type label * ------------------------------------------------------------------------- * ::1/128 LOOPBACK 0 * ::/0 N/A 1 * 2002::/16 N/A 2 * ::/96 COMPATv4 3 * ::ffff:0:0/96 V4MAPPED 4 * fc00::/7 N/A 5 ULA (RFC 4193) * 2001::/32 N/A 6 Teredo (RFC 4380) * 2001:10::/28 N/A 7 ORCHID (RFC 4843) * fec0::/10 N/A 11 Site-local * (deprecated by RFC3879) * 3ffe::/16 N/A 12 6bone * * Note: 0xffffffff is used if we do not have any policies. * Note: Labels for ULA and 6to4 are different from labels listed in RFC6724. */ #define IPV6_ADDR_LABEL_DEFAULT 0xffffffffUL static const __net_initconst struct ip6addrlbl_init_table { const struct in6_addr *prefix; int prefixlen; u32 label; } ip6addrlbl_init_table[] = { { /* ::/0 */ .prefix = &in6addr_any, .label = 1, }, { /* fc00::/7 */ .prefix = &(struct in6_addr){ { { 0xfc } } } , .prefixlen = 7, .label = 5, }, { /* fec0::/10 */ .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, .prefixlen = 10, .label = 11, }, { /* 2002::/16 */ .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, .prefixlen = 16, .label = 2, }, { /* 3ffe::/16 */ .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, .prefixlen = 16, .label = 12, }, { /* 2001::/32 */ .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, .prefixlen = 32, .label = 6, }, { /* 2001:10::/28 */ .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, .prefixlen = 28, .label = 7, }, { /* ::ffff:0:0 */ .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, .prefixlen = 96, .label = 4, }, { /* ::/96 */ .prefix = &in6addr_any, .prefixlen = 96, .label = 3, }, { /* ::1/128 */ .prefix = &in6addr_loopback, .prefixlen = 128, .label = 0, } }; /* Find label */ static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, int addrtype, int ifindex) { if (p->ifindex && p->ifindex != ifindex) return false; if (p->addrtype && p->addrtype != addrtype) return false; if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen)) return false; return true; } static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { struct ip6addrlbl_entry *p; hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { if (__ip6addrlbl_match(p, addr, type, ifindex)) return p; } return NULL; } u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { u32 label; struct ip6addrlbl_entry *p; type &= IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK; rcu_read_lock(); p = __ipv6_addr_label(net, addr, type, ifindex); label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT; rcu_read_unlock(); ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n", __func__, addr, type, ifindex, label); return label; } /* allocate one entry */ static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label) { struct ip6addrlbl_entry *newp; int addrtype; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n", __func__, prefix, prefixlen, ifindex, (unsigned int)label); addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK); switch (addrtype) { case IPV6_ADDR_MAPPED: if (prefixlen > 96) return ERR_PTR(-EINVAL); if (prefixlen < 96) addrtype = 0; break; case IPV6_ADDR_COMPATv4: if (prefixlen != 96) addrtype = 0; break; case IPV6_ADDR_LOOPBACK: if (prefixlen != 128) addrtype = 0; break; } newp = kmalloc(sizeof(*newp), GFP_KERNEL); if (!newp) return ERR_PTR(-ENOMEM); ipv6_addr_prefix(&newp->prefix, prefix, prefixlen); newp->prefixlen = prefixlen; newp->ifindex = ifindex; newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); return newp; } /* add a label */ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, int replace) { struct ip6addrlbl_entry *last = NULL, *p = NULL; struct hlist_node *n; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, replace); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && p->ifindex == newp->ifindex && ipv6_addr_equal(&p->prefix, &newp->prefix)) { if (!replace) { ret = -EEXIST; goto out; } hlist_replace_rcu(&p->list, &newp->list); kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { hlist_add_before_rcu(&newp->list, &p->list); goto out; } last = p; } if (last) hlist_add_behind_rcu(&newp->list, &last->list); else hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) WRITE_ONCE(net->ipv6.ip6addrlbl_table.seq, net->ipv6.ip6addrlbl_table.seq + 1); return ret; } /* add a label */ static int ip6addrlbl_add(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label, int replace) { struct ip6addrlbl_entry *newp; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n", __func__, prefix, prefixlen, ifindex, (unsigned int)label, replace); newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) return PTR_ERR(newp); spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_add(net, newp, replace); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) kfree(newp); return ret; } /* remove a label */ static int __ip6addrlbl_del(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; int ret = -ESRCH; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); ret = 0; break; } } return ret; } static int ip6addrlbl_del(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex) { struct in6_addr prefix_buf; int ret; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); return ret; } /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); spin_lock_init(&net->ipv6.ip6addrlbl_table.lock); INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { err = ip6addrlbl_add(net, ip6addrlbl_init_table[i].prefix, ip6addrlbl_init_table[i].prefixlen, 0, ip6addrlbl_init_table[i].label, 0); if (err) goto err_ip6addrlbl_add; } return 0; err_ip6addrlbl_add: hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); } return err; } static void __net_exit ip6addrlbl_net_exit(struct net *net) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; /* Remove all labels belonging to the exiting net */ spin_lock(&net->ipv6.ip6addrlbl_table.lock); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); } spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } static struct pernet_operations ipv6_addr_label_ops = { .init = ip6addrlbl_net_init, .exit = ip6addrlbl_net_exit, }; int __init ipv6_addr_label_init(void) { return register_pernet_subsys(&ipv6_addr_label_ops); } void ipv6_addr_label_cleanup(void) { unregister_pernet_subsys(&ipv6_addr_label_ops); } static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, }; static bool addrlbl_ifindex_exists(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); rcu_read_unlock(); return dev != NULL; } static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *pfx; u32 label; int err = 0; err = nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); if (err < 0) return err; ifal = nlmsg_data(nlh); if (ifal->ifal_family != AF_INET6 || ifal->ifal_prefixlen > 128) return -EINVAL; if (!tb[IFAL_ADDRESS]) return -EINVAL; pfx = nla_data(tb[IFAL_ADDRESS]); if (!tb[IFAL_LABEL]) return -EINVAL; label = nla_get_u32(tb[IFAL_LABEL]); if (label == IPV6_ADDR_LABEL_DEFAULT) return -EINVAL; switch (nlh->nlmsg_type) { case RTM_NEWADDRLABEL: if (ifal->ifal_index && !addrlbl_ifindex_exists(net, ifal->ifal_index)) return -EINVAL; err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen, ifal->ifal_index, label, nlh->nlmsg_flags & NLM_F_REPLACE); break; case RTM_DELADDRLABEL: err = ip6addrlbl_del(net, pfx, ifal->ifal_prefixlen, ifal->ifal_index); break; default: err = -EOPNOTSUPP; } return err; } static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, int prefixlen, int ifindex, u32 lseq) { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; ifal->ifal_seq = lseq; }; static int ip6addrlbl_fill(struct sk_buff *skb, const struct ip6addrlbl_entry *p, u32 lseq, u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrlblmsg), flags); if (!nlh) return -EMSGSIZE; ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq); if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 || nla_put_u32(skb, IFAL_LABEL, p->label) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifaddrlblmsg *ifal; ifal = nlmsg_payload(nlh, sizeof(*ifal)); if (!ifal) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request"); return -EINVAL; } if (ifal->__ifal_reserved || ifal->ifal_prefixlen || ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifal))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request"); return -EINVAL; } return 0; } static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; int idx = 0, s_idx = cb->args[0]; int err = 0; u32 lseq; if (cb->strict_check) { err = ip6addrlbl_valid_dump_req(nlh, cb->extack); if (err < 0) return err; } rcu_read_lock(); lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq); hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, lseq, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI); if (err < 0) break; } idx++; } rcu_read_unlock(); cb->args[0] = idx; return err; } static inline int ip6addrlbl_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + nla_total_size(16) /* IFAL_ADDRESS */ + nla_total_size(4); /* IFAL_LABEL */ } static int ip6addrlbl_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrlblmsg *ifal; int i, err; ifal = nlmsg_payload(nlh, sizeof(*ifal)); if (!ifal) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); if (err) return err; for (i = 0; i <= IFAL_MAX; i++) { if (!tb[i]) continue; switch (i) { case IFAL_ADDRESS: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in addrlabel get request"); return -EINVAL; } } return 0; } static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *addr; u32 lseq; int err = 0; struct ip6addrlbl_entry *p; struct sk_buff *skb; err = ip6addrlbl_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; ifal = nlmsg_data(nlh); if (ifal->ifal_family != AF_INET6 || ifal->ifal_prefixlen != 128) return -EINVAL; if (ifal->ifal_index && !addrlbl_ifindex_exists(net, ifal->ifal_index)) return -EINVAL; if (!tb[IFAL_ADDRESS]) return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = -ESRCH; rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq); if (p) err = ip6addrlbl_fill(skb, p, lseq, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, 0); rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); } else { err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } return err; } static const struct rtnl_msg_handler ipv6_adddr_label_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWADDRLABEL, .doit = ip6addrlbl_newdel, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELADDRLABEL, .doit = ip6addrlbl_newdel, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETADDRLABEL, .doit = ip6addrlbl_get, .dumpit = ip6addrlbl_dump, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; int __init ipv6_addr_label_rtnl_register(void) { return rtnl_register_many(ipv6_adddr_label_rtnl_msg_handlers); } |
| 12 12 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __MAC802154_DRIVER_OPS #define __MAC802154_DRIVER_OPS #include <linux/types.h> #include <linux/rtnetlink.h> #include <net/mac802154.h> #include "ieee802154_i.h" #include "trace.h" static inline int drv_xmit_async(struct ieee802154_local *local, struct sk_buff *skb) { return local->ops->xmit_async(&local->hw, skb); } static inline int drv_xmit_sync(struct ieee802154_local *local, struct sk_buff *skb) { might_sleep(); return local->ops->xmit_sync(&local->hw, skb); } static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.pan_id = pan_id; trace_802154_drv_set_pan_id(local, pan_id); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_PANID_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_extended_addr(struct ieee802154_local *local, __le64 extended_addr) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.ieee_addr = extended_addr; trace_802154_drv_set_extended_addr(local, extended_addr); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_IEEEADDR_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_short_addr(struct ieee802154_local *local, __le16 short_addr) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.short_addr = short_addr; trace_802154_drv_set_short_addr(local, short_addr); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_SADDR_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_pan_coord(struct ieee802154_local *local, bool is_coord) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.pan_coord = is_coord; trace_802154_drv_set_pan_coord(local, is_coord); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_PANC_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) { int ret; might_sleep(); if (!local->ops->set_promiscuous_mode) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_promiscuous_mode(local, on); ret = local->ops->set_promiscuous_mode(&local->hw, on); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_start(struct ieee802154_local *local, enum ieee802154_filtering_level level, const struct ieee802154_hw_addr_filt *addr_filt) { int ret; might_sleep(); /* setup receive mode parameters e.g. address mode */ if (local->hw.flags & IEEE802154_HW_AFILT) { ret = drv_set_pan_id(local, addr_filt->pan_id); if (ret < 0) return ret; ret = drv_set_short_addr(local, addr_filt->short_addr); if (ret < 0) return ret; ret = drv_set_extended_addr(local, addr_filt->ieee_addr); if (ret < 0) return ret; } switch (level) { case IEEE802154_FILTERING_NONE: fallthrough; case IEEE802154_FILTERING_1_FCS: fallthrough; case IEEE802154_FILTERING_2_PROMISCUOUS: /* TODO: Requires a different receive mode setup e.g. * at86rf233 hardware. */ fallthrough; case IEEE802154_FILTERING_3_SCAN: if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { ret = drv_set_promiscuous_mode(local, true); if (ret < 0) return ret; } else { return -EOPNOTSUPP; } /* In practice other filtering levels can be requested, but as * for now most hardware/drivers only support * IEEE802154_FILTERING_NONE, we fallback to this actual * filtering level in hardware and make our own additional * filtering in mac802154 receive path. * * TODO: Move this logic to the device drivers as hardware may * support more higher level filters. Hardware may also require * a different order how register are set, which could currently * be buggy, so all received parameters need to be moved to the * start() callback and let the driver go into the mode before * it will turn on receive handling. */ local->phy->filtering = IEEE802154_FILTERING_NONE; break; case IEEE802154_FILTERING_4_FRAME_FIELDS: /* Do not error out if IEEE802154_HW_PROMISCUOUS because we * expect the hardware to operate at the level * IEEE802154_FILTERING_4_FRAME_FIELDS anyway. */ if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { ret = drv_set_promiscuous_mode(local, false); if (ret < 0) return ret; } local->phy->filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; break; default: WARN_ON(1); return -EINVAL; } trace_802154_drv_start(local); local->started = true; smp_mb(); ret = local->ops->start(&local->hw); trace_802154_drv_return_int(local, ret); return ret; } static inline void drv_stop(struct ieee802154_local *local) { might_sleep(); trace_802154_drv_stop(local); local->ops->stop(&local->hw); trace_802154_drv_return_void(local); /* sync away all work on the tasklet before clearing started */ tasklet_disable(&local->tasklet); tasklet_enable(&local->tasklet); barrier(); local->started = false; } static inline int drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) { int ret; might_sleep(); trace_802154_drv_set_channel(local, page, channel); ret = local->ops->set_channel(&local->hw, page, channel); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) { int ret; might_sleep(); if (!local->ops->set_txpower) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_tx_power(local, mbm); ret = local->ops->set_txpower(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_cca_mode(struct ieee802154_local *local, const struct wpan_phy_cca *cca) { int ret; might_sleep(); if (!local->ops->set_cca_mode) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_cca_mode(local, cca); ret = local->ops->set_cca_mode(&local->hw, cca); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) { int ret; might_sleep(); if (!local->ops->set_lbt) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_lbt_mode(local, mode); ret = local->ops->set_lbt(&local->hw, mode); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) { int ret; might_sleep(); if (!local->ops->set_cca_ed_level) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_cca_ed_level(local, mbm); ret = local->ops->set_cca_ed_level(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_csma_params(struct ieee802154_local *local, u8 min_be, u8 max_be, u8 max_csma_backoffs) { int ret; might_sleep(); if (!local->ops->set_csma_params) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_csma_params(local, min_be, max_be, max_csma_backoffs); ret = local->ops->set_csma_params(&local->hw, min_be, max_be, max_csma_backoffs); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_max_frame_retries(struct ieee802154_local *local, s8 max_frame_retries) { int ret; might_sleep(); if (!local->ops->set_frame_retries) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_max_frame_retries(local, max_frame_retries); ret = local->ops->set_frame_retries(&local->hw, max_frame_retries); trace_802154_drv_return_int(local, ret); return ret; } #endif /* __MAC802154_DRIVER_OPS */ |
| 16 59 247 248 10 238 37 36 21 16 16 16 4 4 4 4 380 379 379 379 378 381 148 148 3 145 26 4 22 26 15 188 212 2 213 56 55 23 33 18 12 26 26 56 12 12 12 12 2 12 10 12 9 9 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 | // SPDX-License-Identifier: GPL-2.0-only /* * Pluggable TCP congestion control support and newReno * congestion control. * Based on ideas from I/O scheduler support and Web100. * * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org> */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/gfp.h> #include <linux/jhash.h> #include <net/tcp.h> #include <trace/events/tcp.h> static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ struct tcp_congestion_ops *tcp_ca_find(const char *name) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (strcmp(e->name, name) == 0) return e; } return NULL; } void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); trace_tcp_cong_state_set(sk, ca_state); if (icsk->icsk_ca_ops->set_state) icsk->icsk_ca_ops->set_state(sk, ca_state); icsk->icsk_ca_state = ca_state; } /* Must be called with rcu lock held */ static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name) { struct tcp_congestion_ops *ca = tcp_ca_find(name); #ifdef CONFIG_MODULES if (!ca && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); request_module("tcp_%s", name); rcu_read_lock(); ca = tcp_ca_find(name); } #endif return ca; } /* Simple linear search, not much in here. */ struct tcp_congestion_ops *tcp_ca_find_key(u32 key) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (e->key == key) return e; } return NULL; } int tcp_validate_congestion_control(struct tcp_congestion_ops *ca) { /* all algorithms must implement these */ if (!ca->ssthresh || !ca->undo_cwnd || !(ca->cong_avoid || ca->cong_control)) { pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } return 0; } /* Attach new congestion control algorithm to the list * of available options. */ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) { int ret; ret = tcp_validate_congestion_control(ca); if (ret) return ret; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) { pr_notice("%s already registered or non-unique key\n", ca->name); ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); pr_debug("%s registered\n", ca->name); } spin_unlock(&tcp_cong_list_lock); return ret; } EXPORT_SYMBOL_GPL(tcp_register_congestion_control); /* * Remove congestion control algorithm, called from * the module's remove function. Module ref counts are used * to ensure that this can't be done till all sockets using * that method are closed. */ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) { spin_lock(&tcp_cong_list_lock); list_del_rcu(&ca->list); spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module gets removed entirely. * * A try_module_get() should fail by now as our module is * in "going" state since no refs are held anymore and * module_exit() handler being called. */ synchronize_rcu(); } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); /* Replace a registered old ca with a new one. * * The new ca must have the same name as the old one, that has been * registered. */ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); existing = tcp_ca_find_key(old_ca->key); if (ca->key == TCP_CA_UNSPEC || !existing || strcmp(existing->name, ca->name)) { pr_notice("%s not registered or non-unique key\n", ca->name); ret = -EINVAL; } else if (existing != old_ca) { pr_notice("invalid old congestion control algorithm to replace\n"); ret = -EINVAL; } else { /* Add the new one before removing the old one to keep * one implementation available all the time. */ list_add_tail_rcu(&ca->list, &tcp_cong_list); list_del_rcu(&existing->list); pr_debug("%s updated\n", ca->name); } spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module or struct_ops gets removed entirely. */ if (!ret) synchronize_rcu(); return ret; } u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; u32 key = TCP_CA_UNSPEC; might_sleep(); rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (ca) { key = ca->key; *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; } rcu_read_unlock(); return key; } char *tcp_ca_get_name_by_key(u32 key, char *buffer) { const struct tcp_congestion_ops *ca; char *ret = NULL; rcu_read_lock(); ca = tcp_ca_find_key(key); if (ca) { strscpy(buffer, ca->name, TCP_CA_NAME_MAX); ret = buffer; } rcu_read_unlock(); return ret; } /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; icsk->icsk_ca_ops = ca; rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); } void tcp_init_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); icsk->icsk_ca_initialized = 1; } static void tcp_reinit_congestion_control(struct sock *sk, const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } /* Manage refcounts on socket close. */ void tcp_cleanup_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); icsk->icsk_ca_initialized = 0; bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } /* Used by sysctl to change default congestion control */ int tcp_set_default_congestion_control(struct net *net, const char *name) { struct tcp_congestion_ops *ca; const struct tcp_congestion_ops *prev; int ret; rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (!ca) { ret = -ENOENT; } else if (!bpf_try_module_get(ca, ca->owner)) { ret = -EBUSY; } else if (!net_eq(net, &init_net) && !(ca->flags & TCP_CONG_NON_RESTRICTED)) { /* Only init netns can set default to a restricted algorithm */ ret = -EPERM; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) bpf_module_put(prev, prev->owner); ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; } rcu_read_unlock(); return ret; } /* Set default value from kernel configuration at bootup */ static int __init tcp_congestion_default(void) { return tcp_set_default_congestion_control(&init_net, CONFIG_DEFAULT_TCP_CONG); } late_initcall(tcp_congestion_default); /* Build string with list of available congestion control values */ void tcp_get_available_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Get current default congestion control */ void tcp_get_default_congestion_control(struct net *net, char *name) { const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); strscpy(name, ca->name, TCP_CA_NAME_MAX); rcu_read_unlock(); } /* Built list of non-restricted congestion control values */ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; *buf = '\0'; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { if (!(ca->flags & TCP_CONG_NON_RESTRICTED)) continue; offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Change list of non-restricted congestion control */ int tcp_set_allowed_congestion_control(char *val) { struct tcp_congestion_ops *ca; char *saved_clone, *clone, *name; int ret = 0; saved_clone = clone = kstrdup(val, GFP_USER); if (!clone) return -ENOMEM; spin_lock(&tcp_cong_list_lock); /* pass 1 check for bad entries */ while ((name = strsep(&clone, " ")) && *name) { ca = tcp_ca_find(name); if (!ca) { ret = -ENOENT; goto out; } } /* pass 2 clear old values */ list_for_each_entry_rcu(ca, &tcp_cong_list, list) ca->flags &= ~TCP_CONG_NON_RESTRICTED; /* pass 3 mark as allowed */ while ((name = strsep(&val, " ")) && *name) { ca = tcp_ca_find(name); WARN_ON(!ca); if (ca) ca->flags |= TCP_CONG_NON_RESTRICTED; } out: spin_unlock(&tcp_cong_list_lock); kfree(saved_clone); return ret; } /* Change congestion control for socket. If load is false, then it is the * responsibility of the caller to call tcp_init_congestion_control or * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; int err = 0; if (icsk->icsk_ca_dst_locked) return -EPERM; rcu_read_lock(); if (!load) ca = tcp_ca_find(name); else ca = tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) err = -EPERM; else if (!bpf_try_module_get(ca, ca->owner)) err = -EBUSY; else tcp_reinit_congestion_control(sk, ca); out: rcu_read_unlock(); return err; } /* Slow start is used when congestion window is no greater than the slow start * threshold. We base on RFC2581 and also handle stretch ACKs properly. * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but * something better;) a packet is only considered (s)acked in its entirety to * defend the ACK attacks described in the RFC. Slow start processes a stretch * ACK of degree N as if N acks of degree 1 are received back to back except * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ __bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); acked -= cwnd - tcp_snd_cwnd(tp); tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); return acked; } EXPORT_SYMBOL_GPL(tcp_slow_start); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ __bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { /* If credits accumulated at a higher w, apply them gently now. */ if (tp->snd_cwnd_cnt >= w) { tp->snd_cwnd_cnt = 0; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); } tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; tp->snd_cwnd_cnt -= delta * w; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + delta); } tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), tp->snd_cwnd_clamp)); } EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* * TCP Reno congestion control * This is special case used for fallback as well. */ /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ __bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_is_cwnd_limited(sk)) return; /* In "safe" area, increase. */ if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } /* In dangerous area, increase slowly. */ tcp_cong_avoid_ai(tp, tcp_snd_cwnd(tp), acked); } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); /* Slow start threshold is half the congestion window (min 2) */ __bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp) >> 1U, 2U); } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); __bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp), tp->prior_cwnd); } EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd); struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = tcp_reno_undo_cwnd, }; |
| 6 2 1 1 3 1 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * CRC32C chksum * *@Article{castagnoli-crc, * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 * and 32 Parity Bits}}, * journal = IEEE Transactions on Communication, * year = {1993}, * volume = {41}, * number = {6}, * pages = {}, * month = {June}, *} * Used by the iSCSI driver, possibly others, and derived from * the iscsi-crc.c module of the linux-iscsi driver at * http://linux-iscsi.sourceforge.net. * * Following the example of lib/crc32, this function is intended to be * flexible and useful for all users. Modules that currently have their * own crc32c, but hopefully may be able to use this one are: * net/sctp (please add all your doco to here if you change to * use this one!) * <endoflist> * * Copyright (c) 2004 Cisco Systems, Inc. * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/crc32.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 struct chksum_ctx { u32 key; }; struct chksum_desc_ctx { u32 crc; }; /* * Steps through buffer one byte at a time, calculates reflected * crc using table. */ static int chksum_init(struct shash_desc *desc) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = mctx->key; return 0; } /* * Setting the seed allows arbitrary accumulators and flexible XOR policy * If your algorithm starts with ~0, then XOR with ~0 before you set * the seed. */ static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct chksum_ctx *mctx = crypto_shash_ctx(tfm); if (keylen != sizeof(mctx->key)) return -EINVAL; mctx->key = get_unaligned_le32(key); return 0; } static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = crc32c_base(ctx->crc, data, length); return 0; } static int chksum_update_arch(struct shash_desc *desc, const u8 *data, unsigned int length) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = crc32c(ctx->crc, data, length); return 0; } static int chksum_final(struct shash_desc *desc, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); put_unaligned_le32(~ctx->crc, out); return 0; } static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { put_unaligned_le32(~crc32c_base(*crcp, data, len), out); return 0; } static int __chksum_finup_arch(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { put_unaligned_le32(~crc32c(*crcp, data, len), out); return 0; } static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); return __chksum_finup(&ctx->crc, data, len, out); } static int chksum_finup_arch(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); return __chksum_finup_arch(&ctx->crc, data, len, out); } static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); return __chksum_finup(&mctx->key, data, length, out); } static int chksum_digest_arch(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); return __chksum_finup_arch(&mctx->key, data, length, out); } static int crc32c_cra_init(struct crypto_tfm *tfm) { struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); mctx->key = ~0; return 0; } static struct shash_alg algs[] = {{ .digestsize = CHKSUM_DIGEST_SIZE, .setkey = chksum_setkey, .init = chksum_init, .update = chksum_update, .final = chksum_final, .finup = chksum_finup, .digest = chksum_digest, .descsize = sizeof(struct chksum_desc_ctx), .base.cra_name = "crc32c", .base.cra_driver_name = "crc32c-generic", .base.cra_priority = 100, .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .base.cra_blocksize = CHKSUM_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct chksum_ctx), .base.cra_module = THIS_MODULE, .base.cra_init = crc32c_cra_init, }, { .digestsize = CHKSUM_DIGEST_SIZE, .setkey = chksum_setkey, .init = chksum_init, .update = chksum_update_arch, .final = chksum_final, .finup = chksum_finup_arch, .digest = chksum_digest_arch, .descsize = sizeof(struct chksum_desc_ctx), .base.cra_name = "crc32c", .base.cra_driver_name = "crc32c-" __stringify(ARCH), .base.cra_priority = 150, .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .base.cra_blocksize = CHKSUM_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct chksum_ctx), .base.cra_module = THIS_MODULE, .base.cra_init = crc32c_cra_init, }}; static int num_algs; static int __init crc32c_mod_init(void) { /* register the arch flavor only if it differs from the generic one */ num_algs = 1 + ((crc32_optimizations() & CRC32C_OPTIMIZATION) != 0); return crypto_register_shashes(algs, num_algs); } static void __exit crc32c_mod_fini(void) { crypto_unregister_shashes(algs, num_algs); } module_init(crc32c_mod_init); module_exit(crc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); MODULE_ALIAS_CRYPTO("crc32c-generic"); |
| 18021 18101 18064 18021 18029 18103 11792 11779 11826 11775 11781 11770 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/page_ext.h> #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/kmemleak.h> #include <linux/page_owner.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> #include <linux/pgalloc_tag.h> /* * struct page extension * * This is the feature to manage memory for extended data per page. * * Until now, we must modify struct page itself to store extra data per page. * This requires rebuilding the kernel and it is really time consuming process. * And, sometimes, rebuild is impossible due to third party module dependency. * At last, enlarging struct page could cause un-wanted system behaviour change. * * This feature is intended to overcome above mentioned problems. This feature * allocates memory for extended data per page in certain place rather than * the struct page itself. This memory can be accessed by the accessor * functions provided by this code. During the boot process, it checks whether * allocation of huge chunk of memory is needed or not. If not, it avoids * allocating memory at all. With this advantage, we can include this feature * into the kernel in default and can avoid rebuild and solve related problems. * * To help these things to work well, there are two callbacks for clients. One * is the need callback which is mandatory if user wants to avoid useless * memory allocation at boot-time. The other is optional, init callback, which * is used to do proper initialization after memory is allocated. * * The need callback is used to decide whether extended memory allocation is * needed or not. Sometimes users want to deactivate some features in this * boot and extra memory would be unnecessary. In this case, to avoid * allocating huge chunk of memory, each clients represent their need of * extra memory through the need callback. If one of the need callbacks * returns true, it means that someone needs extra memory so that * page extension core should allocates memory for page extension. If * none of need callbacks return true, memory isn't needed at all in this boot * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * * When need callback returns true, page_ext checks if there is a request for * extra memory through size in struct page_ext_operations. If it is non-zero, * extra space is allocated for each page_ext entry and offset is returned to * user through offset in struct page_ext_operations. * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime * of memory for page extension isn't same with memmap for struct page. * Therefore, clients can't store extra data until page extension is * initialized, even if pages are allocated and used freely. This could * cause inadequate state of extra data per page, so, to prevent it, client * can utilize this callback to initialize the state of it correctly. */ #ifdef CONFIG_SPARSEMEM #define PAGE_EXT_INVALID (0x1) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) static bool need_page_idle(void) { return true; } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, .need_shared_flags = true, }; #endif static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif #ifdef CONFIG_MEM_ALLOC_PROFILING &page_alloc_tagging_ops, #endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif }; unsigned long page_ext_size; static unsigned long total_usage; #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG /* * To ensure correct allocation tagging for pages, page_ext should be available * before the first page allocation. Otherwise early task stacks will be * allocated before page_ext initialization and missing tags will be flagged. */ bool early_page_ext __meminitdata = true; #else bool early_page_ext __meminitdata; #endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; return 0; } early_param("early_page_ext", setup_early_page_ext); static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); bool need = false; for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { if (page_ext_ops[i]->need_shared_flags) { page_ext_size = sizeof(struct page_ext); break; } } } for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; } } return need; } static void __init invoke_init_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); for (i = 0; i < entries; i++) { if (page_ext_ops[i]->init) page_ext_ops[i]->init(); } } static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } #ifndef CONFIG_SPARSEMEM void __init page_ext_init_flatmem_late(void) { invoke_init_callbacks(); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { pgdat->node_page_ext = NULL; } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned long index; struct page_ext *base; WARN_ON_ONCE(!rcu_read_lock_held()); base = NODE_DATA(page_to_nid(page))->node_page_ext; /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (unlikely(!base)) return NULL; index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) { struct page_ext *base; unsigned long table_size; unsigned long nr_pages; nr_pages = NODE_DATA(nid)->node_spanned_pages; if (!nr_pages) return 0; /* * Need extra space if node range is not aligned with * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm * checks buddy's status, range could be out of exact node range. */ if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } void __init page_ext_init_flatmem(void) { int nid, fail; if (!invoke_need_callbacks()) return; for_each_online_node(nid) { fail = alloc_node_page_ext(nid); if (fail) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); return; fail: pr_crit("allocation of page_ext failed.\n"); panic("Out of memory"); } #else /* CONFIG_SPARSEMEM */ static bool page_ext_invalid(struct page_ext *page_ext) { return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID); } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); struct page_ext *page_ext = READ_ONCE(section->page_ext); WARN_ON_ONCE(!rcu_read_lock_held()); /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (page_ext_invalid(page_ext)) return NULL; return get_entry(page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) { gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; void *addr = NULL; addr = alloc_pages_exact_nid(nid, size, flags); if (addr) kmemleak_alloc(addr, size, 1, flags); else addr = vzalloc_node(size, nid); if (addr) memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } static int __meminit init_section_page_ext(unsigned long pfn, int nid) { struct mem_section *section; struct page_ext *base; unsigned long table_size; section = __pfn_to_section(pfn); if (section->page_ext) return 0; table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* * The value stored in section->page_ext is (base - pfn) * and it does not point to the memory block allocated above, * causing kmemleak false positives. */ kmemleak_not_leak(base); if (!base) { pr_err("page ext allocation failure\n"); return -ENOMEM; } /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } static void free_page_ext(void *addr) { size_t table_size; struct page *page; table_size = page_ext_size * PAGES_PER_SECTION; memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { vfree(addr); } else { page = virt_to_page(addr); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } } static void __free_page_ext(unsigned long pfn) { struct mem_section *ms; struct page_ext *base; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; base = READ_ONCE(ms->page_ext); /* * page_ext here can be valid while doing the roll back * operation in online_page_ext(). */ if (page_ext_invalid(base)) base = (void *)base - PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, NULL); base = get_entry(base, pfn); free_page_ext(base); } static void __invalidate_page_ext(unsigned long pfn) { struct mem_section *ms; void *val; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; val = (void *)ms->page_ext + PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, val); } static int __meminit online_page_ext(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; int fail = 0; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) fail = init_section_page_ext(pfn, nid); if (!fail) return 0; /* rollback */ end = pfn - PAGES_PER_SECTION; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); return -ENOMEM; } static void __meminit offline_page_ext(unsigned long start_pfn, unsigned long nr_pages) { unsigned long start, end, pfn; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); /* * Freeing of page_ext is done in 3 steps to avoid * use-after-free of it: * 1) Traverse all the sections and mark their page_ext * as invalid. * 2) Wait for all the existing users of page_ext who * started before invalidation to finish. * 3) Free the page_ext. */ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __invalidate_page_ext(pfn); synchronize_rcu(); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); } static int __meminit page_ext_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; int ret = 0; switch (action) { case MEM_GOING_ONLINE: ret = online_page_ext(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; case MEM_OFFLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_CANCEL_ONLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } return notifier_from_errno(ret); } void __init page_ext_init(void) { unsigned long pfn; int nid; if (!invoke_need_callbacks()) return; for_each_node_state(nid, N_MEMORY) { unsigned long start_pfn, end_pfn; start_pfn = node_start_pfn(nid); end_pfn = node_end_pfn(nid); /* * start_pfn and end_pfn may not be aligned to SECTION and the * page->flags of out of node pages are not initialized. So we * scan [start_pfn, the biggest section's pfn < end_pfn) here. */ for (pfn = start_pfn; pfn < end_pfn; pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { if (!pfn_valid(pfn)) continue; /* * Nodes's pfns can be overlapping. * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... */ if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; cond_resched(); } } hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; oom: panic("Out of memory"); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { } #endif /** * page_ext_lookup() - Lookup a page extension for a PFN. * @pfn: PFN of the page we're interested in. * * Must be called with RCU read lock taken and @pfn must be valid. * * Return: NULL if no page_ext exists for this page. */ struct page_ext *page_ext_lookup(unsigned long pfn) { return lookup_page_ext(pfn_to_page(pfn)); } /** * page_ext_get() - Get the extended information for a page. * @page: The page we're interested in. * * Ensures that the page_ext will remain valid until page_ext_put() * is called. * * Return: NULL if no page_ext exists for this page. * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; rcu_read_lock(); page_ext = lookup_page_ext(page); if (!page_ext) { rcu_read_unlock(); return NULL; } return page_ext; } /** * page_ext_put() - Working with page extended information is done. * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. * * Return: None. * Context: Any context with corresponding page_ext_get() is called. */ void page_ext_put(struct page_ext *page_ext) { if (unlikely(!page_ext)) return; rcu_read_unlock(); } |
| 1 3 2 2 2 2 2 2 5 5 2 2 2 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Illinois congestion control. * Home page: * http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html * * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <asm/div64.h> #include <net/tcp.h> #define ALPHA_SHIFT 7 #define ALPHA_SCALE (1u<<ALPHA_SHIFT) #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 #define BETA_SCALE (1u<<BETA_SHIFT) #define BETA_MIN (BETA_SCALE/8) /* 0.125 */ #define BETA_MAX (BETA_SCALE/2) /* 0.5 */ #define BETA_BASE BETA_MAX static int win_thresh __read_mostly = 15; module_param(win_thresh, int, 0); MODULE_PARM_DESC(win_thresh, "Window threshold for starting adaptive sizing"); static int theta __read_mostly = 5; module_param(theta, int, 0); MODULE_PARM_DESC(theta, "# of fast RTT's before full growth"); /* TCP Illinois Parameters */ struct illinois { u64 sum_rtt; /* sum of rtt's measured within last rtt */ u16 cnt_rtt; /* # of rtts measured within last rtt */ u32 base_rtt; /* min of all rtt in usec */ u32 max_rtt; /* max of all rtt in usec */ u32 end_seq; /* right edge of current RTT */ u32 alpha; /* Additive increase */ u32 beta; /* Muliplicative decrease */ u16 acked; /* # packets acked by current ACK */ u8 rtt_above; /* average rtt has gone above threshold */ u8 rtt_low; /* # of rtts measurements below threshold */ }; static void rtt_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); ca->end_seq = tp->snd_nxt; ca->cnt_rtt = 0; ca->sum_rtt = 0; /* TODO: age max_rtt? */ } static void tcp_illinois_init(struct sock *sk) { struct illinois *ca = inet_csk_ca(sk); ca->alpha = ALPHA_MAX; ca->beta = BETA_BASE; ca->base_rtt = 0x7fffffff; ca->max_rtt = 0; ca->acked = 0; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } /* Measure RTT for each ack. */ static void tcp_illinois_acked(struct sock *sk, const struct ack_sample *sample) { struct illinois *ca = inet_csk_ca(sk); s32 rtt_us = sample->rtt_us; ca->acked = sample->pkts_acked; /* dup ack, no rtt sample */ if (rtt_us < 0) return; /* ignore bogus values, this prevents wraparound in alpha math */ if (rtt_us > RTT_MAX) rtt_us = RTT_MAX; /* keep track of minimum RTT seen so far */ if (ca->base_rtt > rtt_us) ca->base_rtt = rtt_us; /* and max */ if (ca->max_rtt < rtt_us) ca->max_rtt = rtt_us; ++ca->cnt_rtt; ca->sum_rtt += rtt_us; } /* Maximum queuing delay */ static inline u32 max_delay(const struct illinois *ca) { return ca->max_rtt - ca->base_rtt; } /* Average queuing delay */ static inline u32 avg_delay(const struct illinois *ca) { u64 t = ca->sum_rtt; do_div(t, ca->cnt_rtt); return t - ca->base_rtt; } /* * Compute value of alpha used for additive increase. * If small window then use 1.0, equivalent to Reno. * * For larger windows, adjust based on average delay. * A. If average delay is at minimum (we are uncongested), * then use large alpha (10.0) to increase faster. * B. If average delay is at maximum (getting congested) * then use small alpha (0.3) * * The result is a convex window growth curve. */ static u32 alpha(struct illinois *ca, u32 da, u32 dm) { u32 d1 = dm / 100; /* Low threshold */ if (da <= d1) { /* If never got out of low delay zone, then use max */ if (!ca->rtt_above) return ALPHA_MAX; /* Wait for 5 good RTT's before allowing alpha to go alpha max. * This prevents one good RTT from causing sudden window increase. */ if (++ca->rtt_low < theta) return ca->alpha; ca->rtt_low = 0; ca->rtt_above = 0; return ALPHA_MAX; } ca->rtt_above = 1; /* * Based on: * * (dm - d1) amin amax * k1 = ------------------- * amax - amin * * (dm - d1) amin * k2 = ---------------- - d1 * amax - amin * * k1 * alpha = ---------- * k2 + da */ dm -= d1; da -= d1; return (dm * ALPHA_MAX) / (dm + (da * (ALPHA_MAX - ALPHA_MIN)) / ALPHA_MIN); } /* * Beta used for multiplicative decrease. * For small window sizes returns same value as Reno (0.5) * * If delay is small (10% of max) then beta = 1/8 * If delay is up to 80% of max then beta = 1/2 * In between is a linear function */ static u32 beta(u32 da, u32 dm) { u32 d2, d3; d2 = dm / 10; if (da <= d2) return BETA_MIN; d3 = (8 * dm) / 10; if (da >= d3 || d3 <= d2) return BETA_MAX; /* * Based on: * * bmin d3 - bmax d2 * k3 = ------------------- * d3 - d2 * * bmax - bmin * k4 = ------------- * d3 - d2 * * b = k3 + k4 da */ return (BETA_MIN * d3 - BETA_MAX * d2 + (BETA_MAX - BETA_MIN) * da) / (d3 - d2); } /* Update alpha and beta values once per RTT */ static void update_params(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (tcp_snd_cwnd(tp) < win_thresh) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; } else if (ca->cnt_rtt > 0) { u32 dm = max_delay(ca); u32 da = avg_delay(ca); ca->alpha = alpha(ca, da, dm); ca->beta = beta(da, dm); } rtt_reset(sk); } /* * In case of loss, reset to default values */ static void tcp_illinois_state(struct sock *sk, u8 new_state) { struct illinois *ca = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } } /* * Increase window in response to successful acknowledgment. */ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (after(ack, ca->end_seq)) update_params(sk); /* RFC2861 only increase cwnd if fully utilized */ if (!tcp_is_cwnd_limited(sk)) return; /* In slow start */ if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { u32 delta; /* snd_cwnd_cnt is # of packets since last cwnd increment */ tp->snd_cwnd_cnt += ca->acked; ca->acked = 1; /* This is close approximation of: * tp->snd_cwnd += alpha/tp->snd_cwnd */ delta = (tp->snd_cwnd_cnt * ca->alpha) >> ALPHA_SHIFT; if (delta >= tcp_snd_cwnd(tp)) { tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp) + delta / tcp_snd_cwnd(tp), (u32)tp->snd_cwnd_clamp)); tp->snd_cwnd_cnt = 0; } } } static u32 tcp_illinois_ssthresh(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); u32 decr; /* Multiplicative decrease */ decr = (tcp_snd_cwnd(tp) * ca->beta) >> BETA_SHIFT; return max(tcp_snd_cwnd(tp) - decr, 2U); } /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct illinois *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = ca->cnt_rtt; info->vegas.tcpv_minrtt = ca->base_rtt; info->vegas.tcpv_rtt = 0; if (info->vegas.tcpv_rttcnt > 0) { u64 t = ca->sum_rtt; do_div(t, info->vegas.tcpv_rttcnt); info->vegas.tcpv_rtt = t; } *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcp_illinois __read_mostly = { .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, .pkts_acked = tcp_illinois_acked, .owner = THIS_MODULE, .name = "illinois", }; static int __init tcp_illinois_register(void) { BUILD_BUG_ON(sizeof(struct illinois) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_illinois); } static void __exit tcp_illinois_unregister(void) { tcp_unregister_congestion_control(&tcp_illinois); } module_init(tcp_illinois_register); module_exit(tcp_illinois_unregister); MODULE_AUTHOR("Stephen Hemminger, Shao Liu"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Illinois"); MODULE_VERSION("1.0"); |
| 13 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 1999-2002 Vojtech Pavlik */ #ifndef _INPUT_H #define _INPUT_H #include <linux/time.h> #include <linux/list.h> #include <uapi/linux/input.h> /* Implementation details, userspace should not care about these */ #define ABS_MT_FIRST ABS_MT_TOUCH_MAJOR #define ABS_MT_LAST ABS_MT_TOOL_Y /* * In-kernel definitions. */ #include <linux/device.h> #include <linux/fs.h> #include <linux/timer.h> #include <linux/mod_devicetable.h> struct input_dev_poller; /** * struct input_value - input value representation * @type: type of value (EV_KEY, EV_ABS, etc) * @code: the value code * @value: the value */ struct input_value { __u16 type; __u16 code; __s32 value; }; enum input_clock_type { INPUT_CLK_REAL = 0, INPUT_CLK_MONO, INPUT_CLK_BOOT, INPUT_CLK_MAX }; /** * struct input_dev - represents an input device * @name: name of the device * @phys: physical path to the device in the system hierarchy * @uniq: unique identification code for the device (if device has it) * @id: id of the device (struct input_id) * @propbit: bitmap of device properties and quirks * @evbit: bitmap of types of events supported by the device (EV_KEY, * EV_REL, etc.) * @keybit: bitmap of keys/buttons this device has * @relbit: bitmap of relative axes for the device * @absbit: bitmap of absolute axes for the device * @mscbit: bitmap of miscellaneous events supported by the device * @ledbit: bitmap of leds present on the device * @sndbit: bitmap of sound effects supported by the device * @ffbit: bitmap of force feedback effects supported by the device * @swbit: bitmap of switches present on the device * @hint_events_per_packet: average number of events generated by the * device in a packet (between EV_SYN/SYN_REPORT events). Used by * event handlers to estimate size of the buffer needed to hold * events. * @keycodemax: size of keycode table * @keycodesize: size of elements in keycode table * @keycode: map of scancodes to keycodes for this device * @getkeycode: optional legacy method to retrieve current keymap. * @setkeycode: optional method to alter current keymap, used to implement * sparse keymaps. If not supplied default mechanism will be used. * The method is being called while holding event_lock and thus must * not sleep * @ff: force feedback structure associated with the device if device * supports force feedback effects * @poller: poller structure associated with the device if device is * set up to use polling mode * @repeat_key: stores key code of the last key pressed; used to implement * software autorepeat * @timer: timer for software autorepeat * @rep: current values for autorepeat parameters (delay, rate) * @mt: pointer to multitouch state * @absinfo: array of &struct input_absinfo elements holding information * about absolute axes (current value, min, max, flat, fuzz, * resolution) * @key: reflects current state of device's keys/buttons * @led: reflects current state of device's LEDs * @snd: reflects current state of sound effects * @sw: reflects current state of device's switches * @open: this method is called when the very first user calls * input_open_device(). The driver must prepare the device * to start generating events (start polling thread, * request an IRQ, submit URB, etc.). The meaning of open() is * to start providing events to the input core. * @close: this method is called when the very last user calls * input_close_device(). The meaning of close() is to stop * providing events to the input core. * @flush: purges the device. Most commonly used to get rid of force * feedback effects loaded into the device when disconnecting * from it * @event: event handler for events sent _to_ the device, like EV_LED * or EV_SND. The device is expected to carry out the requested * action (turn on a LED, play sound, etc.) The call is protected * by @event_lock and must not sleep * @grab: input handle that currently has the device grabbed (via * EVIOCGRAB ioctl). When a handle grabs a device it becomes sole * recipient for all input events coming from the device * @event_lock: this spinlock is taken when input core receives * and processes a new event for the device (in input_event()). * Code that accesses and/or modifies parameters of a device * (such as keymap or absmin, absmax, absfuzz, etc.) after device * has been registered with input core must take this lock. * @mutex: serializes calls to open(), close() and flush() methods * @users: stores number of users (input handlers) that opened this * device. It is used by input_open_device() and input_close_device() * to make sure that dev->open() is only called when the first * user opens device and dev->close() is called when the very * last user closes the device * @going_away: marks devices that are in a middle of unregistering and * causes input_open_device*() fail with -ENODEV. * @dev: driver model's view of this device * @h_list: list of input handles associated with the device. When * accessing the list dev->mutex must be held * @node: used to place the device onto input_dev_list * @num_vals: number of values queued in the current frame * @max_vals: maximum number of values queued in a frame * @vals: array of values queued in the current frame * @devres_managed: indicates that devices is managed with devres framework * and needs not be explicitly unregistered or freed. * @timestamp: storage for a timestamp set by input_set_timestamp called * by a driver * @inhibited: indicates that the input device is inhibited. If that is * the case then input core ignores any events generated by the device. * Device's close() is called when it is being inhibited and its open() * is called when it is being uninhibited. */ struct input_dev { const char *name; const char *phys; const char *uniq; struct input_id id; unsigned long propbit[BITS_TO_LONGS(INPUT_PROP_CNT)]; unsigned long evbit[BITS_TO_LONGS(EV_CNT)]; unsigned long keybit[BITS_TO_LONGS(KEY_CNT)]; unsigned long relbit[BITS_TO_LONGS(REL_CNT)]; unsigned long absbit[BITS_TO_LONGS(ABS_CNT)]; unsigned long mscbit[BITS_TO_LONGS(MSC_CNT)]; unsigned long ledbit[BITS_TO_LONGS(LED_CNT)]; unsigned long sndbit[BITS_TO_LONGS(SND_CNT)]; unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; unsigned long swbit[BITS_TO_LONGS(SW_CNT)]; unsigned int hint_events_per_packet; unsigned int keycodemax; unsigned int keycodesize; void *keycode; int (*setkeycode)(struct input_dev *dev, const struct input_keymap_entry *ke, unsigned int *old_keycode); int (*getkeycode)(struct input_dev *dev, struct input_keymap_entry *ke); struct ff_device *ff; struct input_dev_poller *poller; unsigned int repeat_key; struct timer_list timer; int rep[REP_CNT]; struct input_mt *mt; struct input_absinfo *absinfo; unsigned long key[BITS_TO_LONGS(KEY_CNT)]; unsigned long led[BITS_TO_LONGS(LED_CNT)]; unsigned long snd[BITS_TO_LONGS(SND_CNT)]; unsigned long sw[BITS_TO_LONGS(SW_CNT)]; int (*open)(struct input_dev *dev); void (*close)(struct input_dev *dev); int (*flush)(struct input_dev *dev, struct file *file); int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value); struct input_handle __rcu *grab; spinlock_t event_lock; struct mutex mutex; unsigned int users; bool going_away; struct device dev; struct list_head h_list; struct list_head node; unsigned int num_vals; unsigned int max_vals; struct input_value *vals; bool devres_managed; ktime_t timestamp[INPUT_CLK_MAX]; bool inhibited; }; #define to_input_dev(d) container_of(d, struct input_dev, dev) /* * Verify that we are in sync with input_device_id mod_devicetable.h #defines */ #if EV_MAX != INPUT_DEVICE_ID_EV_MAX #error "EV_MAX and INPUT_DEVICE_ID_EV_MAX do not match" #endif #if KEY_MIN_INTERESTING != INPUT_DEVICE_ID_KEY_MIN_INTERESTING #error "KEY_MIN_INTERESTING and INPUT_DEVICE_ID_KEY_MIN_INTERESTING do not match" #endif #if KEY_MAX != INPUT_DEVICE_ID_KEY_MAX #error "KEY_MAX and INPUT_DEVICE_ID_KEY_MAX do not match" #endif #if REL_MAX != INPUT_DEVICE_ID_REL_MAX #error "REL_MAX and INPUT_DEVICE_ID_REL_MAX do not match" #endif #if ABS_MAX != INPUT_DEVICE_ID_ABS_MAX #error "ABS_MAX and INPUT_DEVICE_ID_ABS_MAX do not match" #endif #if MSC_MAX != INPUT_DEVICE_ID_MSC_MAX #error "MSC_MAX and INPUT_DEVICE_ID_MSC_MAX do not match" #endif #if LED_MAX != INPUT_DEVICE_ID_LED_MAX #error "LED_MAX and INPUT_DEVICE_ID_LED_MAX do not match" #endif #if SND_MAX != INPUT_DEVICE_ID_SND_MAX #error "SND_MAX and INPUT_DEVICE_ID_SND_MAX do not match" #endif #if FF_MAX != INPUT_DEVICE_ID_FF_MAX #error "FF_MAX and INPUT_DEVICE_ID_FF_MAX do not match" #endif #if SW_MAX != INPUT_DEVICE_ID_SW_MAX #error "SW_MAX and INPUT_DEVICE_ID_SW_MAX do not match" #endif #if INPUT_PROP_MAX != INPUT_DEVICE_ID_PROP_MAX #error "INPUT_PROP_MAX and INPUT_DEVICE_ID_PROP_MAX do not match" #endif #define INPUT_DEVICE_ID_MATCH_DEVICE \ (INPUT_DEVICE_ID_MATCH_BUS | INPUT_DEVICE_ID_MATCH_VENDOR | INPUT_DEVICE_ID_MATCH_PRODUCT) #define INPUT_DEVICE_ID_MATCH_DEVICE_AND_VERSION \ (INPUT_DEVICE_ID_MATCH_DEVICE | INPUT_DEVICE_ID_MATCH_VERSION) struct input_handle; /** * struct input_handler - implements one of interfaces for input devices * @private: driver-specific data * @event: event handler. This method is being called by input core with * interrupts disabled and dev->event_lock spinlock held and so * it may not sleep * @events: event sequence handler. This method is being called by * input core with interrupts disabled and dev->event_lock * spinlock held and so it may not sleep. The method must return * number of events passed to it. * @filter: similar to @event; separates normal event handlers from * "filters". * @match: called after comparing device's id with handler's id_table * to perform fine-grained matching between device and handler * @connect: called when attaching a handler to an input device * @disconnect: disconnects a handler from input device * @start: starts handler for given handle. This function is called by * input core right after connect() method and also when a process * that "grabbed" a device releases it * @passive_observer: set to %true by drivers only interested in observing * data stream from devices if there are other users present. Such * drivers will not result in starting underlying hardware device * when input_open_device() is called for their handles * @legacy_minors: set to %true by drivers using legacy minor ranges * @minor: beginning of range of 32 legacy minors for devices this driver * can provide * @name: name of the handler, to be shown in /proc/bus/input/handlers * @id_table: pointer to a table of input_device_ids this driver can * handle * @h_list: list of input handles associated with the handler * @node: for placing the driver onto input_handler_list * * Input handlers attach to input devices and create input handles. There * are likely several handlers attached to any given input device at the * same time. All of them will get their copy of input event generated by * the device. * * The very same structure is used to implement input filters. Input core * allows filters to run first and will not pass event to regular handlers * if any of the filters indicate that the event should be filtered (by * returning %true from their filter() method). * * Note that input core serializes calls to connect() and disconnect() * methods. */ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); unsigned int (*events)(struct input_handle *handle, struct input_value *vals, unsigned int count); bool (*filter)(struct input_handle *handle, unsigned int type, unsigned int code, int value); bool (*match)(struct input_handler *handler, struct input_dev *dev); int (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); void (*disconnect)(struct input_handle *handle); void (*start)(struct input_handle *handle); bool passive_observer; bool legacy_minors; int minor; const char *name; const struct input_device_id *id_table; struct list_head h_list; struct list_head node; }; /** * struct input_handle - links input device with an input handler * @private: handler-specific data * @open: counter showing whether the handle is 'open', i.e. should deliver * events from its device * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle * @handle_events: event sequence handler. It is set up by the input core * according to event handling method specified in the @handler. See * input_handle_setup_event_handler(). * This method is being called by the input core with interrupts disabled * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { void *private; int open; const char *name; struct input_dev *dev; struct input_handler *handler; unsigned int (*handle_events)(struct input_handle *handle, struct input_value *vals, unsigned int count); struct list_head d_node; struct list_head h_node; }; struct input_dev __must_check *input_allocate_device(void); struct input_dev __must_check *devm_input_allocate_device(struct device *); void input_free_device(struct input_dev *dev); static inline struct input_dev *input_get_device(struct input_dev *dev) { return dev ? to_input_dev(get_device(&dev->dev)) : NULL; } static inline void input_put_device(struct input_dev *dev) { if (dev) put_device(&dev->dev); } static inline void *input_get_drvdata(struct input_dev *dev) { return dev_get_drvdata(&dev->dev); } static inline void input_set_drvdata(struct input_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } int __must_check input_register_device(struct input_dev *); void input_unregister_device(struct input_dev *); void input_reset_device(struct input_dev *); int input_setup_polling(struct input_dev *dev, void (*poll_fn)(struct input_dev *dev)); void input_set_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_min_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_max_poll_interval(struct input_dev *dev, unsigned int interval); int input_get_poll_interval(struct input_dev *dev); int __must_check input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); int __must_check input_get_new_minor(int legacy_base, unsigned int legacy_num, bool allow_dynamic); void input_free_minor(unsigned int minor); int input_handler_for_each_handle(struct input_handler *, void *data, int (*fn)(struct input_handle *, void *)); int input_register_handle(struct input_handle *); void input_unregister_handle(struct input_handle *); int input_grab_device(struct input_handle *); void input_release_device(struct input_handle *); int input_open_device(struct input_handle *); void input_close_device(struct input_handle *); int input_flush_device(struct input_handle *handle, struct file *file); void input_set_timestamp(struct input_dev *dev, ktime_t timestamp); ktime_t *input_get_timestamp(struct input_dev *dev); void input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); void input_inject_event(struct input_handle *handle, unsigned int type, unsigned int code, int value); static inline void input_report_key(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_KEY, code, !!value); } static inline void input_report_rel(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_REL, code, value); } static inline void input_report_abs(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_ABS, code, value); } static inline void input_report_ff_status(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_FF_STATUS, code, value); } static inline void input_report_switch(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_SW, code, !!value); } static inline void input_sync(struct input_dev *dev) { input_event(dev, EV_SYN, SYN_REPORT, 0); } static inline void input_mt_sync(struct input_dev *dev) { input_event(dev, EV_SYN, SYN_MT_REPORT, 0); } void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code); /** * input_set_events_per_packet - tell handlers about the driver event rate * @dev: the input device used by the driver * @n_events: the average number of events between calls to input_sync() * * If the event rate sent from a device is unusually large, use this * function to set the expected event rate. This will allow handlers * to set up an appropriate buffer size for the event stream, in order * to minimize information loss. */ static inline void input_set_events_per_packet(struct input_dev *dev, int n_events) { dev->hint_events_per_packet = n_events; } void input_alloc_absinfo(struct input_dev *dev); void input_set_abs_params(struct input_dev *dev, unsigned int axis, int min, int max, int fuzz, int flat); void input_copy_abs(struct input_dev *dst, unsigned int dst_axis, const struct input_dev *src, unsigned int src_axis); #define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ static inline int input_abs_get_##_suffix(struct input_dev *dev, \ unsigned int axis) \ { \ return dev->absinfo ? dev->absinfo[axis]._item : 0; \ } \ \ static inline void input_abs_set_##_suffix(struct input_dev *dev, \ unsigned int axis, int val) \ { \ input_alloc_absinfo(dev); \ if (dev->absinfo) \ dev->absinfo[axis]._item = val; \ } INPUT_GENERATE_ABS_ACCESSORS(val, value) INPUT_GENERATE_ABS_ACCESSORS(min, minimum) INPUT_GENERATE_ABS_ACCESSORS(max, maximum) INPUT_GENERATE_ABS_ACCESSORS(fuzz, fuzz) INPUT_GENERATE_ABS_ACCESSORS(flat, flat) INPUT_GENERATE_ABS_ACCESSORS(res, resolution) int input_scancode_to_scalar(const struct input_keymap_entry *ke, unsigned int *scancode); int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke); int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke); bool input_match_device_id(const struct input_dev *dev, const struct input_device_id *id); void input_enable_softrepeat(struct input_dev *dev, int delay, int period); bool input_device_enabled(struct input_dev *dev); extern const struct class input_class; /** * struct ff_device - force-feedback part of an input device * @upload: Called to upload an new effect into device * @erase: Called to erase an effect from device * @playback: Called to request device to start playing specified effect * @set_gain: Called to set specified gain * @set_autocenter: Called to auto-center device * @destroy: called by input core when parent input device is being * destroyed * @private: driver-specific data, will be freed automatically * @ffbit: bitmap of force feedback capabilities truly supported by * device (not emulated like ones in input_dev->ffbit) * @mutex: mutex for serializing access to the device * @max_effects: maximum number of effects supported by device * @effects: pointer to an array of effects currently loaded into device * @effect_owners: array of effect owners; when file handle owning * an effect gets closed the effect is automatically erased * * Every force-feedback device must implement upload() and playback() * methods; erase() is optional. set_gain() and set_autocenter() need * only be implemented if driver sets up FF_GAIN and FF_AUTOCENTER * bits. * * Note that playback(), set_gain() and set_autocenter() are called with * dev->event_lock spinlock held and interrupts off and thus may not * sleep. */ struct ff_device { int (*upload)(struct input_dev *dev, struct ff_effect *effect, struct ff_effect *old); int (*erase)(struct input_dev *dev, int effect_id); int (*playback)(struct input_dev *dev, int effect_id, int value); void (*set_gain)(struct input_dev *dev, u16 gain); void (*set_autocenter)(struct input_dev *dev, u16 magnitude); void (*destroy)(struct ff_device *); void *private; unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; struct mutex mutex; int max_effects; struct ff_effect *effects; struct file *effect_owners[] __counted_by(max_effects); }; int input_ff_create(struct input_dev *dev, unsigned int max_effects); void input_ff_destroy(struct input_dev *dev); int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); int input_ff_flush(struct input_dev *dev, struct file *file); int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); #endif |
| 117 117 117 117 117 31 31 29 3 5 5 5 5 5 2 2 2 2 5 5 5 5 5 5 5 2 7 8 8 1 1 2 5 2 7 8 8 8 8 3 8 8 10 7 2 2 8 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 | /* * cgroup_freezer.c - control group freezer subsystem * * Copyright IBM Corporation, 2007 * * Author : Cedric Le Goater <clg@fr.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. */ #include <linux/export.h> #include <linux/slab.h> #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/cpu.h> /* * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared * for "THAWED". FREEZING_PARENT is set if the parent freezer is FREEZING * for whatever reason. IOW, a cgroup has FREEZING_PARENT set if one of * its ancestors has FREEZING_SELF set. */ enum freezer_state_flags { CGROUP_FREEZER_ONLINE = (1 << 0), /* freezer is fully online */ CGROUP_FREEZING_SELF = (1 << 1), /* this freezer is freezing */ CGROUP_FREEZING_PARENT = (1 << 2), /* the parent freezer is freezing */ CGROUP_FROZEN = (1 << 3), /* this and its descendants frozen */ /* mask for all FREEZING flags */ CGROUP_FREEZING = CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT, }; struct freezer { struct cgroup_subsys_state css; unsigned int state; }; static DEFINE_MUTEX(freezer_mutex); static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) { return css ? container_of(css, struct freezer, css) : NULL; } static inline struct freezer *task_freezer(struct task_struct *task) { return css_freezer(task_css(task, freezer_cgrp_id)); } static struct freezer *parent_freezer(struct freezer *freezer) { return css_freezer(freezer->css.parent); } bool cgroup_freezing(struct task_struct *task) { bool ret; unsigned int state; rcu_read_lock(); /* Check if the cgroup is still FREEZING, but not FROZEN. The extra * !FROZEN check is required, because the FREEZING bit is not cleared * when the state FROZEN is reached. */ state = task_freezer(task)->state; ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN); rcu_read_unlock(); return ret; } static const char *freezer_state_strs(unsigned int state) { if (state & CGROUP_FROZEN) return "FROZEN"; if (state & CGROUP_FREEZING) return "FREEZING"; return "THAWED"; }; static struct cgroup_subsys_state * freezer_css_alloc(struct cgroup_subsys_state *parent_css) { struct freezer *freezer; freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL); if (!freezer) return ERR_PTR(-ENOMEM); return &freezer->css; } /** * freezer_css_online - commit creation of a freezer css * @css: css being created * * We're committing to creation of @css. Mark it online and inherit * parent's freezing state while holding cpus read lock and freezer_mutex. */ static int freezer_css_online(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer); cpus_read_lock(); mutex_lock(&freezer_mutex); freezer->state |= CGROUP_FREEZER_ONLINE; if (parent && (parent->state & CGROUP_FREEZING)) { freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; static_branch_inc_cpuslocked(&freezer_active); } mutex_unlock(&freezer_mutex); cpus_read_unlock(); return 0; } /** * freezer_css_offline - initiate destruction of a freezer css * @css: css being destroyed * * @css is going away. Mark it dead and decrement freezer_active if * it was holding one. */ static void freezer_css_offline(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); cpus_read_lock(); mutex_lock(&freezer_mutex); if (freezer->state & CGROUP_FREEZING) static_branch_dec_cpuslocked(&freezer_active); freezer->state = 0; mutex_unlock(&freezer_mutex); cpus_read_unlock(); } static void freezer_css_free(struct cgroup_subsys_state *css) { kfree(css_freezer(css)); } /* * Tasks can be migrated into a different freezer anytime regardless of its * current state. freezer_attach() is responsible for making new tasks * conform to the current state. * * Freezer state changes and task migration are synchronized via * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ static void freezer_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); /* * Make the new tasks conform to the current state of @new_css. * For simplicity, when migrating any task to a FROZEN cgroup, we * revert it to FREEZING and let update_if_frozen() determine the * correct state later. * * Tasks in @tset are on @new_css but may not conform to its * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ cgroup_taskset_for_each(task, new_css, tset) { struct freezer *freezer = css_freezer(new_css); if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { /* clear FROZEN and propagate upwards */ while (freezer && (freezer->state & CGROUP_FROZEN)) { freezer->state &= ~CGROUP_FROZEN; freezer = parent_freezer(freezer); } freeze_task(task); } } mutex_unlock(&freezer_mutex); } /** * freezer_fork - cgroup post fork callback * @task: a task which has just been forked * * @task has just been created and should conform to the current state of * the cgroup_freezer it belongs to. This function may race against * freezer_attach(). Losing to freezer_attach() means that we don't have * to do anything as freezer_attach() will put @task into the appropriate * state. */ static void freezer_fork(struct task_struct *task) { struct freezer *freezer; /* * The root cgroup is non-freezable, so we can skip locking the * freezer. This is safe regardless of race with task migration. * If we didn't race or won, skipping is obviously the right thing * to do. If we lost and root is the new cgroup, noop is still the * right thing to do. */ if (task_css_is_root(task, freezer_cgrp_id)) return; mutex_lock(&freezer_mutex); rcu_read_lock(); freezer = task_freezer(task); if (freezer->state & CGROUP_FREEZING) freeze_task(task); rcu_read_unlock(); mutex_unlock(&freezer_mutex); } /** * update_if_frozen - update whether a cgroup finished freezing * @css: css of interest * * Once FREEZING is initiated, transition to FROZEN is lazily updated by * calling this function. If the current state is FREEZING but not FROZEN, * this function checks whether all tasks of this cgroup and the descendant * cgroups finished freezing and, if so, sets FROZEN. * * The caller is responsible for grabbing RCU read lock and calling * update_if_frozen() on all descendants prior to invoking this function. * * Task states and freezer state might disagree while tasks are being * migrated into or out of @css, so we can't verify task states against * @freezer state here. See freezer_attach() for details. */ static void update_if_frozen(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct cgroup_subsys_state *pos; struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZING) || (freezer->state & CGROUP_FROZEN)) return; /* are all (live) children frozen? */ rcu_read_lock(); css_for_each_child(pos, css) { struct freezer *child = css_freezer(pos); if ((child->state & CGROUP_FREEZER_ONLINE) && !(child->state & CGROUP_FROZEN)) { rcu_read_unlock(); return; } } rcu_read_unlock(); /* are all tasks frozen? */ css_task_iter_start(css, 0, &it); while ((task = css_task_iter_next(&it))) { if (freezing(task) && !frozen(task)) goto out_iter_end; } freezer->state |= CGROUP_FROZEN; out_iter_end: css_task_iter_end(&it); } static int freezer_read(struct seq_file *m, void *v) { struct cgroup_subsys_state *css = seq_css(m), *pos; mutex_lock(&freezer_mutex); rcu_read_lock(); /* update states bottom-up */ css_for_each_descendant_post(pos, css) { if (!css_tryget_online(pos)) continue; rcu_read_unlock(); update_if_frozen(pos); rcu_read_lock(); css_put(pos); } rcu_read_unlock(); mutex_unlock(&freezer_mutex); seq_puts(m, freezer_state_strs(css_freezer(css)->state)); seq_putc(m, '\n'); return 0; } static void freeze_cgroup(struct freezer *freezer) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) freeze_task(task); css_task_iter_end(&it); } static void unfreeze_cgroup(struct freezer *freezer) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) __thaw_task(task); css_task_iter_end(&it); } /** * freezer_apply_state - apply state change to a single cgroup_freezer * @freezer: freezer to apply state change to * @freeze: whether to freeze or unfreeze * @state: CGROUP_FREEZING_* flag to set or clear * * Set or clear @state on @cgroup according to @freeze, and perform * freezing or thawing as necessary. */ static void freezer_apply_state(struct freezer *freezer, bool freeze, unsigned int state) { /* also synchronizes against task migration, see freezer_attach() */ lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZER_ONLINE)) return; if (freeze) { if (!(freezer->state & CGROUP_FREEZING)) static_branch_inc_cpuslocked(&freezer_active); freezer->state |= state; freeze_cgroup(freezer); } else { bool was_freezing = freezer->state & CGROUP_FREEZING; freezer->state &= ~state; if (!(freezer->state & CGROUP_FREEZING)) { freezer->state &= ~CGROUP_FROZEN; if (was_freezing) static_branch_dec_cpuslocked(&freezer_active); unfreeze_cgroup(freezer); } } } /** * freezer_change_state - change the freezing state of a cgroup_freezer * @freezer: freezer of interest * @freeze: whether to freeze or thaw * * Freeze or thaw @freezer according to @freeze. The operations are * recursive - all descendants of @freezer will be affected. */ static void freezer_change_state(struct freezer *freezer, bool freeze) { struct cgroup_subsys_state *pos; cpus_read_lock(); /* * Update all its descendants in pre-order traversal. Each * descendant will try to inherit its parent's FREEZING state as * CGROUP_FREEZING_PARENT. */ mutex_lock(&freezer_mutex); rcu_read_lock(); css_for_each_descendant_pre(pos, &freezer->css) { struct freezer *pos_f = css_freezer(pos); struct freezer *parent = parent_freezer(pos_f); if (!css_tryget_online(pos)) continue; rcu_read_unlock(); if (pos_f == freezer) freezer_apply_state(pos_f, freeze, CGROUP_FREEZING_SELF); else freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING, CGROUP_FREEZING_PARENT); rcu_read_lock(); css_put(pos); } rcu_read_unlock(); mutex_unlock(&freezer_mutex); cpus_read_unlock(); } static ssize_t freezer_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { bool freeze; buf = strstrip(buf); if (strcmp(buf, freezer_state_strs(0)) == 0) freeze = false; else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) { pr_info_once("Freezing with imperfect legacy cgroup freezer. " "See cgroup.freeze of cgroup v2\n"); freeze = true; } else return -EINVAL; freezer_change_state(css_freezer(of_css(of)), freeze); return nbytes; } static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_SELF); } static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_PARENT); } static struct cftype files[] = { { .name = "state", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = freezer_read, .write = freezer_write, }, { .name = "self_freezing", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = freezer_self_freezing_read, }, { .name = "parent_freezing", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = freezer_parent_freezing_read, }, { } /* terminate */ }; struct cgroup_subsys freezer_cgrp_subsys = { .css_alloc = freezer_css_alloc, .css_online = freezer_css_online, .css_offline = freezer_css_offline, .css_free = freezer_css_free, .attach = freezer_attach, .fork = freezer_fork, .legacy_cftypes = files, }; |
| 194 28 81 34944 113 7398 16138 1967 2848 202 8 8 81 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/ucopysize.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL #define mask_user_address(src) (src) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. * * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (should_fail_usercopy()) goto fail; if (can_do_masked_user_access()) from = mask_user_address(from); else { if (!access_ok(from, n)) goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); if (likely(!res)) return 0; fail: memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } /** * copy_struct_to_user: copy a struct to userspace * @dst: Destination address, in userspace. This buffer must be @ksize * bytes long. * @usize: (Alleged) size of @dst struct. * @src: Source address, in kernel space. * @ksize: Size of @src struct. * @ignored_trailing: Set to %true if there was a non-zero byte in @src that * userspace cannot see because they are using an smaller struct. * * Copies a struct from kernel space to userspace, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * Some syscalls may wish to make sure that userspace knows about everything in * the struct, and if there is a non-zero value that userspce doesn't know * about, they want to return an error (such as -EMSGSIZE) or have some other * fallback (such as adding a "you're missing some information" flag). If * @ignored_trailing is non-%NULL, it will be set to %true if there was a * non-zero byte that could not be copied to userspace (ie. was past @usize). * * While unconditionally returning an error in this case is the simplest * solution, for maximum backward compatibility you should try to only return * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. * Note that structure sizes can change due to header changes and simple * recompilations without code changes(!), so if you care about * @ignored_trailing you probably want to make sure that any new field data is * associated with a flag. Otherwise you might assume that a program knows * about data it does not. * * @ksize is just sizeof(*src), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) * { * int err; * bool ignored_trailing; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * // ... modify karg somehow ... * * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), * &ignored_trailing); * if (err) * return err; * if (ignored_trailing) * return -EMSGSIZE: * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the kernel is trying to pass userspace a newer * struct than it supports. Thus we only copy the interoperable portions * (@usize) and ignore the rest (but @ignored_trailing is set to %true if * any of the trailing (@ksize - @usize) bytes are non-zero). * * If @usize > @ksize, then the kernel is trying to pass userspace an older * struct than userspace supports. In order to make sure the * unknown-to-the-kernel fields don't contain garbage values, we zero the * trailing (@usize - @ksize) bytes. * * Returns (in all cases, some data may have been copied): * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_to_user(void __user *dst, size_t usize, const void *src, size_t ksize, bool *ignored_trailing) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize > ksize) { if (clear_user(dst + size, rest)) return -EFAULT; } if (ignored_trailing) *ignored_trailing = ksize < usize && memchr_inv(src + size, 0, rest) != NULL; /* Copy the interoperable parts of the struct. */ if (copy_to_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 | /* * Copyright (c) 2006 Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/completion.h> #include <linux/dma-mapping.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/random.h> #include <rdma/ib_cache.h> #include "sa.h" static int mcast_add_one(struct ib_device *device); static void mcast_remove_one(struct ib_device *device, void *client_data); static struct ib_client mcast_client = { .name = "ib_multicast", .add = mcast_add_one, .remove = mcast_remove_one }; static struct ib_sa_client sa_client; static struct workqueue_struct *mcast_wq; static union ib_gid mgid0; struct mcast_device; struct mcast_port { struct mcast_device *dev; spinlock_t lock; struct rb_root table; refcount_t refcount; struct completion comp; u32 port_num; }; struct mcast_device { struct ib_device *device; struct ib_event_handler event_handler; int start_port; int end_port; struct mcast_port port[]; }; enum mcast_state { MCAST_JOINING, MCAST_MEMBER, MCAST_ERROR, }; enum mcast_group_state { MCAST_IDLE, MCAST_BUSY, MCAST_GROUP_ERROR, MCAST_PKEY_EVENT }; enum { MCAST_INVALID_PKEY_INDEX = 0xFFFF }; struct mcast_member; struct mcast_group { struct ib_sa_mcmember_rec rec; struct rb_node node; struct mcast_port *port; spinlock_t lock; struct work_struct work; struct list_head pending_list; struct list_head active_list; struct mcast_member *last_join; int members[NUM_JOIN_MEMBERSHIP_TYPES]; atomic_t refcount; enum mcast_group_state state; struct ib_sa_query *query; u16 pkey_index; u8 leave_state; int retries; }; struct mcast_member { struct ib_sa_multicast multicast; struct ib_sa_client *client; struct mcast_group *group; struct list_head list; enum mcast_state state; refcount_t refcount; struct completion comp; }; static void join_handler(int status, struct ib_sa_mcmember_rec *rec, void *context); static void leave_handler(int status, struct ib_sa_mcmember_rec *rec, void *context); static struct mcast_group *mcast_find(struct mcast_port *port, union ib_gid *mgid) { struct rb_node *node = port->table.rb_node; struct mcast_group *group; int ret; while (node) { group = rb_entry(node, struct mcast_group, node); ret = memcmp(mgid->raw, group->rec.mgid.raw, sizeof *mgid); if (!ret) return group; if (ret < 0) node = node->rb_left; else node = node->rb_right; } return NULL; } static struct mcast_group *mcast_insert(struct mcast_port *port, struct mcast_group *group, int allow_duplicates) { struct rb_node **link = &port->table.rb_node; struct rb_node *parent = NULL; struct mcast_group *cur_group; int ret; while (*link) { parent = *link; cur_group = rb_entry(parent, struct mcast_group, node); ret = memcmp(group->rec.mgid.raw, cur_group->rec.mgid.raw, sizeof group->rec.mgid); if (ret < 0) link = &(*link)->rb_left; else if (ret > 0) link = &(*link)->rb_right; else if (allow_duplicates) link = &(*link)->rb_left; else return cur_group; } rb_link_node(&group->node, parent, link); rb_insert_color(&group->node, &port->table); return NULL; } static void deref_port(struct mcast_port *port) { if (refcount_dec_and_test(&port->refcount)) complete(&port->comp); } static void release_group(struct mcast_group *group) { struct mcast_port *port = group->port; unsigned long flags; spin_lock_irqsave(&port->lock, flags); if (atomic_dec_and_test(&group->refcount)) { rb_erase(&group->node, &port->table); spin_unlock_irqrestore(&port->lock, flags); kfree(group); deref_port(port); } else spin_unlock_irqrestore(&port->lock, flags); } static void deref_member(struct mcast_member *member) { if (refcount_dec_and_test(&member->refcount)) complete(&member->comp); } static void queue_join(struct mcast_member *member) { struct mcast_group *group = member->group; unsigned long flags; spin_lock_irqsave(&group->lock, flags); list_add_tail(&member->list, &group->pending_list); if (group->state == MCAST_IDLE) { group->state = MCAST_BUSY; atomic_inc(&group->refcount); queue_work(mcast_wq, &group->work); } spin_unlock_irqrestore(&group->lock, flags); } /* * A multicast group has four types of members: full member, non member, * sendonly non member and sendonly full member. * We need to keep track of the number of members of each * type based on their join state. Adjust the number of members the belong to * the specified join states. */ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc) { int i; for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1) if (join_state & 0x1) group->members[i] += inc; } /* * If a multicast group has zero members left for a particular join state, but * the group is still a member with the SA, we need to leave that join state. * Determine which join states we still belong to, but that do not have any * active members. */ static u8 get_leave_state(struct mcast_group *group) { u8 leave_state = 0; int i; for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++) if (!group->members[i]) leave_state |= (0x1 << i); return leave_state & group->rec.join_state; } static int check_selector(ib_sa_comp_mask comp_mask, ib_sa_comp_mask selector_mask, ib_sa_comp_mask value_mask, u8 selector, u8 src_value, u8 dst_value) { int err; if (!(comp_mask & selector_mask) || !(comp_mask & value_mask)) return 0; switch (selector) { case IB_SA_GT: err = (src_value <= dst_value); break; case IB_SA_LT: err = (src_value >= dst_value); break; case IB_SA_EQ: err = (src_value != dst_value); break; default: err = 0; break; } return err; } static int cmp_rec(struct ib_sa_mcmember_rec *src, struct ib_sa_mcmember_rec *dst, ib_sa_comp_mask comp_mask) { /* MGID must already match */ if (comp_mask & IB_SA_MCMEMBER_REC_PORT_GID && memcmp(&src->port_gid, &dst->port_gid, sizeof src->port_gid)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_QKEY && src->qkey != dst->qkey) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_MLID && src->mlid != dst->mlid) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_MTU_SELECTOR, IB_SA_MCMEMBER_REC_MTU, dst->mtu_selector, src->mtu, dst->mtu)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_TRAFFIC_CLASS && src->traffic_class != dst->traffic_class) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_PKEY && src->pkey != dst->pkey) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_RATE_SELECTOR, IB_SA_MCMEMBER_REC_RATE, dst->rate_selector, src->rate, dst->rate)) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME_SELECTOR, IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME, dst->packet_life_time_selector, src->packet_life_time, dst->packet_life_time)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_SL && src->sl != dst->sl) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_FLOW_LABEL && src->flow_label != dst->flow_label) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_HOP_LIMIT && src->hop_limit != dst->hop_limit) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_SCOPE && src->scope != dst->scope) return -EINVAL; /* join_state checked separately, proxy_join ignored */ return 0; } static int send_join(struct mcast_group *group, struct mcast_member *member) { struct mcast_port *port = group->port; int ret; group->last_join = member; ret = ib_sa_mcmember_rec_query(&sa_client, port->dev->device, port->port_num, IB_MGMT_METHOD_SET, &member->multicast.rec, member->multicast.comp_mask, 3000, GFP_KERNEL, join_handler, group, &group->query); return (ret > 0) ? 0 : ret; } static int send_leave(struct mcast_group *group, u8 leave_state) { struct mcast_port *port = group->port; struct ib_sa_mcmember_rec rec; int ret; rec = group->rec; rec.join_state = leave_state; group->leave_state = leave_state; ret = ib_sa_mcmember_rec_query(&sa_client, port->dev->device, port->port_num, IB_SA_METHOD_DELETE, &rec, IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_JOIN_STATE, 3000, GFP_KERNEL, leave_handler, group, &group->query); return (ret > 0) ? 0 : ret; } static void join_group(struct mcast_group *group, struct mcast_member *member, u8 join_state) { member->state = MCAST_MEMBER; adjust_membership(group, join_state, 1); group->rec.join_state |= join_state; member->multicast.rec = group->rec; member->multicast.rec.join_state = join_state; list_move(&member->list, &group->active_list); } static int fail_join(struct mcast_group *group, struct mcast_member *member, int status) { spin_lock_irq(&group->lock); list_del_init(&member->list); spin_unlock_irq(&group->lock); return member->multicast.callback(status, &member->multicast); } static void process_group_error(struct mcast_group *group) { struct mcast_member *member; int ret = 0; u16 pkey_index; if (group->state == MCAST_PKEY_EVENT) ret = ib_find_pkey(group->port->dev->device, group->port->port_num, be16_to_cpu(group->rec.pkey), &pkey_index); spin_lock_irq(&group->lock); if (group->state == MCAST_PKEY_EVENT && !ret && group->pkey_index == pkey_index) goto out; while (!list_empty(&group->active_list)) { member = list_entry(group->active_list.next, struct mcast_member, list); refcount_inc(&member->refcount); list_del_init(&member->list); adjust_membership(group, member->multicast.rec.join_state, -1); member->state = MCAST_ERROR; spin_unlock_irq(&group->lock); ret = member->multicast.callback(-ENETRESET, &member->multicast); deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); spin_lock_irq(&group->lock); } group->rec.join_state = 0; out: group->state = MCAST_BUSY; spin_unlock_irq(&group->lock); } static void mcast_work_handler(struct work_struct *work) { struct mcast_group *group; struct mcast_member *member; struct ib_sa_multicast *multicast; int status, ret; u8 join_state; group = container_of(work, typeof(*group), work); retest: spin_lock_irq(&group->lock); while (!list_empty(&group->pending_list) || (group->state != MCAST_BUSY)) { if (group->state != MCAST_BUSY) { spin_unlock_irq(&group->lock); process_group_error(group); goto retest; } member = list_entry(group->pending_list.next, struct mcast_member, list); multicast = &member->multicast; join_state = multicast->rec.join_state; refcount_inc(&member->refcount); if (join_state == (group->rec.join_state & join_state)) { status = cmp_rec(&group->rec, &multicast->rec, multicast->comp_mask); if (!status) join_group(group, member, join_state); else list_del_init(&member->list); spin_unlock_irq(&group->lock); ret = multicast->callback(status, multicast); } else { spin_unlock_irq(&group->lock); status = send_join(group, member); if (!status) { deref_member(member); return; } ret = fail_join(group, member, status); } deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); spin_lock_irq(&group->lock); } join_state = get_leave_state(group); if (join_state) { group->rec.join_state &= ~join_state; spin_unlock_irq(&group->lock); if (send_leave(group, join_state)) goto retest; } else { group->state = MCAST_IDLE; spin_unlock_irq(&group->lock); release_group(group); } } /* * Fail a join request if it is still active - at the head of the pending queue. */ static void process_join_error(struct mcast_group *group, int status) { struct mcast_member *member; int ret; spin_lock_irq(&group->lock); member = list_entry(group->pending_list.next, struct mcast_member, list); if (group->last_join == member) { refcount_inc(&member->refcount); list_del_init(&member->list); spin_unlock_irq(&group->lock); ret = member->multicast.callback(status, &member->multicast); deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); } else spin_unlock_irq(&group->lock); } static void join_handler(int status, struct ib_sa_mcmember_rec *rec, void *context) { struct mcast_group *group = context; u16 pkey_index = MCAST_INVALID_PKEY_INDEX; if (status) process_join_error(group, status); else { int mgids_changed, is_mgid0; if (ib_find_pkey(group->port->dev->device, group->port->port_num, be16_to_cpu(rec->pkey), &pkey_index)) pkey_index = MCAST_INVALID_PKEY_INDEX; spin_lock_irq(&group->port->lock); if (group->state == MCAST_BUSY && group->pkey_index == MCAST_INVALID_PKEY_INDEX) group->pkey_index = pkey_index; mgids_changed = memcmp(&rec->mgid, &group->rec.mgid, sizeof(group->rec.mgid)); group->rec = *rec; if (mgids_changed) { rb_erase(&group->node, &group->port->table); is_mgid0 = !memcmp(&mgid0, &group->rec.mgid, sizeof(mgid0)); mcast_insert(group->port, group, is_mgid0); } spin_unlock_irq(&group->port->lock); } mcast_work_handler(&group->work); } static void leave_handler(int status, struct ib_sa_mcmember_rec *rec, void *context) { struct mcast_group *group = context; if (status && group->retries > 0 && !send_leave(group, group->leave_state)) group->retries--; else mcast_work_handler(&group->work); } static struct mcast_group *acquire_group(struct mcast_port *port, union ib_gid *mgid, gfp_t gfp_mask) { struct mcast_group *group, *cur_group; unsigned long flags; int is_mgid0; is_mgid0 = !memcmp(&mgid0, mgid, sizeof mgid0); if (!is_mgid0) { spin_lock_irqsave(&port->lock, flags); group = mcast_find(port, mgid); if (group) goto found; spin_unlock_irqrestore(&port->lock, flags); } group = kzalloc(sizeof *group, gfp_mask); if (!group) return NULL; group->retries = 3; group->port = port; group->rec.mgid = *mgid; group->pkey_index = MCAST_INVALID_PKEY_INDEX; INIT_LIST_HEAD(&group->pending_list); INIT_LIST_HEAD(&group->active_list); INIT_WORK(&group->work, mcast_work_handler); spin_lock_init(&group->lock); spin_lock_irqsave(&port->lock, flags); cur_group = mcast_insert(port, group, is_mgid0); if (cur_group) { kfree(group); group = cur_group; } else refcount_inc(&port->refcount); found: atomic_inc(&group->refcount); spin_unlock_irqrestore(&port->lock, flags); return group; } /* * We serialize all join requests to a single group to make our lives much * easier. Otherwise, two users could try to join the same group * simultaneously, with different configurations, one could leave while the * join is in progress, etc., which makes locking around error recovery * difficult. */ struct ib_sa_multicast * ib_sa_join_multicast(struct ib_sa_client *client, struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, ib_sa_comp_mask comp_mask, gfp_t gfp_mask, int (*callback)(int status, struct ib_sa_multicast *multicast), void *context) { struct mcast_device *dev; struct mcast_member *member; struct ib_sa_multicast *multicast; int ret; dev = ib_get_client_data(device, &mcast_client); if (!dev) return ERR_PTR(-ENODEV); member = kmalloc(sizeof *member, gfp_mask); if (!member) return ERR_PTR(-ENOMEM); ib_sa_client_get(client); member->client = client; member->multicast.rec = *rec; member->multicast.comp_mask = comp_mask; member->multicast.callback = callback; member->multicast.context = context; init_completion(&member->comp); refcount_set(&member->refcount, 1); member->state = MCAST_JOINING; member->group = acquire_group(&dev->port[port_num - dev->start_port], &rec->mgid, gfp_mask); if (!member->group) { ret = -ENOMEM; goto err; } /* * The user will get the multicast structure in their callback. They * could then free the multicast structure before we can return from * this routine. So we save the pointer to return before queuing * any callback. */ multicast = &member->multicast; queue_join(member); return multicast; err: ib_sa_client_put(client); kfree(member); return ERR_PTR(ret); } EXPORT_SYMBOL(ib_sa_join_multicast); void ib_sa_free_multicast(struct ib_sa_multicast *multicast) { struct mcast_member *member; struct mcast_group *group; member = container_of(multicast, struct mcast_member, multicast); group = member->group; spin_lock_irq(&group->lock); if (member->state == MCAST_MEMBER) adjust_membership(group, multicast->rec.join_state, -1); list_del_init(&member->list); if (group->state == MCAST_IDLE) { group->state = MCAST_BUSY; spin_unlock_irq(&group->lock); /* Continue to hold reference on group until callback */ queue_work(mcast_wq, &group->work); } else { spin_unlock_irq(&group->lock); release_group(group); } deref_member(member); wait_for_completion(&member->comp); ib_sa_client_put(member->client); kfree(member); } EXPORT_SYMBOL(ib_sa_free_multicast); int ib_sa_get_mcmember_rec(struct ib_device *device, u32 port_num, union ib_gid *mgid, struct ib_sa_mcmember_rec *rec) { struct mcast_device *dev; struct mcast_port *port; struct mcast_group *group; unsigned long flags; int ret = 0; dev = ib_get_client_data(device, &mcast_client); if (!dev) return -ENODEV; port = &dev->port[port_num - dev->start_port]; spin_lock_irqsave(&port->lock, flags); group = mcast_find(port, mgid); if (group) *rec = group->rec; else ret = -EADDRNOTAVAIL; spin_unlock_irqrestore(&port->lock, flags); return ret; } EXPORT_SYMBOL(ib_sa_get_mcmember_rec); /** * ib_init_ah_from_mcmember - Initialize AH attribute from multicast * member record and gid of the device. * @device: RDMA device * @port_num: Port of the rdma device to consider * @rec: Multicast member record to use * @ndev: Optional netdevice, applicable only for RoCE * @gid_type: GID type to consider * @ah_attr: AH attribute to fillup on successful completion * * ib_init_ah_from_mcmember() initializes AH attribute based on multicast * member record and other device properties. On success the caller is * responsible to call rdma_destroy_ah_attr on the ah_attr. Returns 0 on * success or appropriate error code. * */ int ib_init_ah_from_mcmember(struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, struct net_device *ndev, enum ib_gid_type gid_type, struct rdma_ah_attr *ah_attr) { const struct ib_gid_attr *sgid_attr; /* GID table is not based on the netdevice for IB link layer, * so ignore ndev during search. */ if (rdma_protocol_ib(device, port_num)) ndev = NULL; else if (!rdma_protocol_roce(device, port_num)) return -EINVAL; sgid_attr = rdma_find_gid_by_port(device, &rec->port_gid, gid_type, port_num, ndev); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); memset(ah_attr, 0, sizeof(*ah_attr)); ah_attr->type = rdma_ah_find_type(device, port_num); rdma_ah_set_dlid(ah_attr, be16_to_cpu(rec->mlid)); rdma_ah_set_sl(ah_attr, rec->sl); rdma_ah_set_port_num(ah_attr, port_num); rdma_ah_set_static_rate(ah_attr, rec->rate); rdma_move_grh_sgid_attr(ah_attr, &rec->mgid, be32_to_cpu(rec->flow_label), rec->hop_limit, rec->traffic_class, sgid_attr); return 0; } EXPORT_SYMBOL(ib_init_ah_from_mcmember); static void mcast_groups_event(struct mcast_port *port, enum mcast_group_state state) { struct mcast_group *group; struct rb_node *node; unsigned long flags; spin_lock_irqsave(&port->lock, flags); for (node = rb_first(&port->table); node; node = rb_next(node)) { group = rb_entry(node, struct mcast_group, node); spin_lock(&group->lock); if (group->state == MCAST_IDLE) { atomic_inc(&group->refcount); queue_work(mcast_wq, &group->work); } if (group->state != MCAST_GROUP_ERROR) group->state = state; spin_unlock(&group->lock); } spin_unlock_irqrestore(&port->lock, flags); } static void mcast_event_handler(struct ib_event_handler *handler, struct ib_event *event) { struct mcast_device *dev; int index; dev = container_of(handler, struct mcast_device, event_handler); if (!rdma_cap_ib_mcast(dev->device, event->element.port_num)) return; index = event->element.port_num - dev->start_port; switch (event->event) { case IB_EVENT_PORT_ERR: case IB_EVENT_LID_CHANGE: case IB_EVENT_CLIENT_REREGISTER: mcast_groups_event(&dev->port[index], MCAST_GROUP_ERROR); break; case IB_EVENT_PKEY_CHANGE: mcast_groups_event(&dev->port[index], MCAST_PKEY_EVENT); break; default: break; } } static int mcast_add_one(struct ib_device *device) { struct mcast_device *dev; struct mcast_port *port; int i; int count = 0; dev = kmalloc(struct_size(dev, port, device->phys_port_cnt), GFP_KERNEL); if (!dev) return -ENOMEM; dev->start_port = rdma_start_port(device); dev->end_port = rdma_end_port(device); for (i = 0; i <= dev->end_port - dev->start_port; i++) { if (!rdma_cap_ib_mcast(device, dev->start_port + i)) continue; port = &dev->port[i]; port->dev = dev; port->port_num = dev->start_port + i; spin_lock_init(&port->lock); port->table = RB_ROOT; init_completion(&port->comp); refcount_set(&port->refcount, 1); ++count; } if (!count) { kfree(dev); return -EOPNOTSUPP; } dev->device = device; ib_set_client_data(device, &mcast_client, dev); INIT_IB_EVENT_HANDLER(&dev->event_handler, device, mcast_event_handler); ib_register_event_handler(&dev->event_handler); return 0; } static void mcast_remove_one(struct ib_device *device, void *client_data) { struct mcast_device *dev = client_data; struct mcast_port *port; int i; ib_unregister_event_handler(&dev->event_handler); flush_workqueue(mcast_wq); for (i = 0; i <= dev->end_port - dev->start_port; i++) { if (rdma_cap_ib_mcast(device, dev->start_port + i)) { port = &dev->port[i]; deref_port(port); wait_for_completion(&port->comp); } } kfree(dev); } int mcast_init(void) { int ret; mcast_wq = alloc_ordered_workqueue("ib_mcast", WQ_MEM_RECLAIM); if (!mcast_wq) return -ENOMEM; ib_sa_register_client(&sa_client); ret = ib_register_client(&mcast_client); if (ret) goto err; return 0; err: ib_sa_unregister_client(&sa_client); destroy_workqueue(mcast_wq); return ret; } void mcast_cleanup(void) { ib_unregister_client(&mcast_client); ib_sa_unregister_client(&sa_client); destroy_workqueue(mcast_wq); } |
| 94 144 147 416 571 115 11 106 115 58 1215 4 4 1212 1213 1212 14 50 12 40 49 1155 532 624 1393 1391 731 678 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/l3mdev.h - L3 master device API * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ #include <net/dst.h> #include <net/fib_rules.h> enum l3mdev_type { L3MDEV_TYPE_UNSPEC, L3MDEV_TYPE_VRF, __L3MDEV_TYPE_MAX }; #define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1) typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d); /** * struct l3mdev_ops - l3mdev operations * * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_l3_rcv: Hook in L3 receive path * * @l3mdev_l3_out: Hook in L3 output path * * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, struct sock *sk, struct sk_buff *skb, u16 proto); /* IPv6 ops */ struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id); int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); static inline bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) { return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) && fl->flowi_l3mdev == iifindex; } static inline bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) { return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF && fl->flowi_l3mdev == oifindex; } void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; rcu_read_lock(); ifindex = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); return ifindex; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { struct net_device *dev; int rc = 0; if (ifindex) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); } return rc; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; struct net_device *master; if (!dev) return NULL; if (netif_is_l3_master(dev)) master = dev; else if (netif_is_l3_slave(dev)) master = netdev_master_upper_dev_get_rcu(dev); else master = NULL; return master; } int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { rcu_read_lock(); ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); rcu_read_unlock(); return ifindex; } u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) { u32 tb_id; rcu_read_lock(); tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; bool rc = false; if (ifindex == 0) return false; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_l3_master(dev); rcu_read_unlock(); return rc; } struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) { struct net_device *master = NULL; if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); else if (netif_is_l3_master(skb->dev) || netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto); return skb; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET6); } static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { struct net_device *dev = skb_dst(skb)->dev; if (netif_is_l3_slave(dev)) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); rcu_read_unlock(); } return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET6); } #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex(struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { return 0; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } static inline struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { return NULL; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { return -EOPNOTSUPP; } static inline void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { } static inline int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { return -ENODEV; } static inline int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { return 1; } static inline bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) { return false; } static inline bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) { return false; } static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { } #endif #endif /* _NET_L3MDEV_H_ */ |
| 149 160 144 26 2 146 160 149 11 11 11 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); if (folio && user_alloc_needs_zeroing()) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memcpy_folio(struct folio *dst_folio, size_t dst_off, struct folio *src_folio, size_t src_off, size_t len) { VM_BUG_ON(dst_off + len > folio_size(dst_folio)); VM_BUG_ON(src_off + len > folio_size(src_folio)); do { char *dst = kmap_local_folio(dst_folio, dst_off); const char *src = kmap_local_folio(src_folio, src_off); size_t chunk = len; if (folio_test_highmem(dst_folio) && chunk > PAGE_SIZE - offset_in_page(dst_off)) chunk = PAGE_SIZE - offset_in_page(dst_off); if (folio_test_highmem(src_folio) && chunk > PAGE_SIZE - offset_in_page(src_off)) chunk = PAGE_SIZE - offset_in_page(src_off); memcpy(dst, src, chunk); kunmap_local(src); kunmap_local(dst); dst_off += chunk; src_off += chunk; len -= chunk; } while (len > 0); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 1 1 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/svc.c * * High-level RPC service routines * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> * * Multiple threads pools and NUMAisation * Copyright (c) 2006 Silicon Graphics, Inc. * by Greg Banks <gnb@melbourne.sgi.com> */ #include <linux/linkage.h> #include <linux/sched/signal.h> #include <linux/errno.h> #include <linux/net.h> #include <linux/in.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/slab.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/bc_xprt.h> #include <trace/events/sunrpc.h> #include "fail.h" #include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_SVCDSP static void svc_unregister(const struct svc_serv *serv, struct net *net); #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL /* * Mode for mapping cpus to pools. */ enum { SVC_POOL_AUTO = -1, /* choose one of the others */ SVC_POOL_GLOBAL, /* no mapping, just a single global pool * (legacy & UP mode) */ SVC_POOL_PERCPU, /* one pool per cpu */ SVC_POOL_PERNODE /* one pool per numa node */ }; /* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ struct svc_pool_map { int count; /* How many svc_servs use us */ int mode; /* Note: int not enum to avoid * warnings about "enumeration value * not handled in switch" */ unsigned int npools; unsigned int *pool_to; /* maps pool id to cpu or node */ unsigned int *to_pool; /* maps cpu or node to pool id */ }; static struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int __param_set_pool_mode(const char *val, struct svc_pool_map *m) { int err, mode; mutex_lock(&svc_pool_map_mutex); err = 0; if (!strncmp(val, "auto", 4)) mode = SVC_POOL_AUTO; else if (!strncmp(val, "global", 6)) mode = SVC_POOL_GLOBAL; else if (!strncmp(val, "percpu", 6)) mode = SVC_POOL_PERCPU; else if (!strncmp(val, "pernode", 7)) mode = SVC_POOL_PERNODE; else err = -EINVAL; if (err) goto out; if (m->count == 0) m->mode = mode; else if (mode != m->mode) err = -EBUSY; out: mutex_unlock(&svc_pool_map_mutex); return err; } static int param_set_pool_mode(const char *val, const struct kernel_param *kp) { struct svc_pool_map *m = kp->arg; return __param_set_pool_mode(val, m); } int sunrpc_set_pool_mode(const char *val) { return __param_set_pool_mode(val, &svc_pool_map); } EXPORT_SYMBOL(sunrpc_set_pool_mode); /** * sunrpc_get_pool_mode - get the current pool_mode for the host * @buf: where to write the current pool_mode * @size: size of @buf * * Grab the current pool_mode from the svc_pool_map and write * the resulting string to @buf. Returns the number of characters * written to @buf (a'la snprintf()). */ int sunrpc_get_pool_mode(char *buf, size_t size) { struct svc_pool_map *m = &svc_pool_map; switch (m->mode) { case SVC_POOL_AUTO: return snprintf(buf, size, "auto"); case SVC_POOL_GLOBAL: return snprintf(buf, size, "global"); case SVC_POOL_PERCPU: return snprintf(buf, size, "percpu"); case SVC_POOL_PERNODE: return snprintf(buf, size, "pernode"); default: return snprintf(buf, size, "%d", m->mode); } } EXPORT_SYMBOL(sunrpc_get_pool_mode); static int param_get_pool_mode(char *buf, const struct kernel_param *kp) { char str[16]; int len; len = sunrpc_get_pool_mode(str, ARRAY_SIZE(str)); /* Ensure we have room for newline and NUL */ len = min_t(int, len, ARRAY_SIZE(str) - 2); /* tack on the newline */ str[len] = '\n'; str[len + 1] = '\0'; return sysfs_emit(buf, "%s", str); } module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode, &svc_pool_map, 0644); /* * Detect best pool mapping mode heuristically, * according to the machine's topology. */ static int svc_pool_map_choose_mode(void) { unsigned int node; if (nr_online_nodes > 1) { /* * Actually have multiple NUMA nodes, * so split pools on NUMA node boundaries */ return SVC_POOL_PERNODE; } node = first_online_node; if (nr_cpus_node(node) > 2) { /* * Non-trivial SMP, or CONFIG_NUMA on * non-NUMA hardware, e.g. with a generic * x86_64 kernel on Xeons. In this case we * want to divide the pools on cpu boundaries. */ return SVC_POOL_PERCPU; } /* default: one global pool */ return SVC_POOL_GLOBAL; } /* * Allocate the to_pool[] and pool_to[] arrays. * Returns 0 on success or an errno. */ static int svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) { m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); if (!m->to_pool) goto fail; m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); if (!m->pool_to) goto fail_free; return 0; fail_free: kfree(m->to_pool); m->to_pool = NULL; fail: return -ENOMEM; } /* * Initialise the pool map for SVC_POOL_PERCPU mode. * Returns number of pools or <0 on error. */ static int svc_pool_map_init_percpu(struct svc_pool_map *m) { unsigned int maxpools = nr_cpu_ids; unsigned int pidx = 0; unsigned int cpu; int err; err = svc_pool_map_alloc_arrays(m, maxpools); if (err) return err; for_each_online_cpu(cpu) { BUG_ON(pidx >= maxpools); m->to_pool[cpu] = pidx; m->pool_to[pidx] = cpu; pidx++; } /* cpus brought online later all get mapped to pool0, sorry */ return pidx; }; /* * Initialise the pool map for SVC_POOL_PERNODE mode. * Returns number of pools or <0 on error. */ static int svc_pool_map_init_pernode(struct svc_pool_map *m) { unsigned int maxpools = nr_node_ids; unsigned int pidx = 0; unsigned int node; int err; err = svc_pool_map_alloc_arrays(m, maxpools); if (err) return err; for_each_node_with_cpus(node) { /* some architectures (e.g. SN2) have cpuless nodes */ BUG_ON(pidx > maxpools); m->to_pool[node] = pidx; m->pool_to[pidx] = node; pidx++; } /* nodes brought online later all get mapped to pool0, sorry */ return pidx; } /* * Add a reference to the global map of cpus to pools (and * vice versa) if pools are in use. * Initialise the map if we're the first user. * Returns the number of pools. If this is '1', no reference * was taken. */ static unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; int npools = -1; mutex_lock(&svc_pool_map_mutex); if (m->count++) { mutex_unlock(&svc_pool_map_mutex); return m->npools; } if (m->mode == SVC_POOL_AUTO) m->mode = svc_pool_map_choose_mode(); switch (m->mode) { case SVC_POOL_PERCPU: npools = svc_pool_map_init_percpu(m); break; case SVC_POOL_PERNODE: npools = svc_pool_map_init_pernode(m); break; } if (npools <= 0) { /* default, or memory allocation failure */ npools = 1; m->mode = SVC_POOL_GLOBAL; } m->npools = npools; mutex_unlock(&svc_pool_map_mutex); return npools; } /* * Drop a reference to the global map of cpus to pools. * When the last reference is dropped, the map data is * freed; this allows the sysadmin to change the pool. */ static void svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; mutex_lock(&svc_pool_map_mutex); if (!--m->count) { kfree(m->to_pool); m->to_pool = NULL; kfree(m->pool_to); m->pool_to = NULL; m->npools = 0; } mutex_unlock(&svc_pool_map_mutex); } static int svc_pool_map_get_node(unsigned int pidx) { const struct svc_pool_map *m = &svc_pool_map; if (m->count) { if (m->mode == SVC_POOL_PERCPU) return cpu_to_node(m->pool_to[pidx]); if (m->mode == SVC_POOL_PERNODE) return m->pool_to[pidx]; } return NUMA_NO_NODE; } /* * Set the given thread's cpus_allowed mask so that it * will only run on cpus in the given pool. */ static inline void svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) { struct svc_pool_map *m = &svc_pool_map; unsigned int node = m->pool_to[pidx]; /* * The caller checks for sv_nrpools > 1, which * implies that we've been initialized. */ WARN_ON_ONCE(m->count == 0); if (m->count == 0) return; switch (m->mode) { case SVC_POOL_PERCPU: { set_cpus_allowed_ptr(task, cpumask_of(node)); break; } case SVC_POOL_PERNODE: { set_cpus_allowed_ptr(task, cpumask_of_node(node)); break; } } } /** * svc_pool_for_cpu - Select pool to run a thread on this cpu * @serv: An RPC service * * Use the active CPU and the svc_pool_map's mode setting to * select the svc thread pool to use. Once initialized, the * svc_pool_map does not change. * * Return value: * A pointer to an svc_pool */ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) { struct svc_pool_map *m = &svc_pool_map; int cpu = raw_smp_processor_id(); unsigned int pidx = 0; if (serv->sv_nrpools <= 1) return serv->sv_pools; switch (m->mode) { case SVC_POOL_PERCPU: pidx = m->to_pool[cpu]; break; case SVC_POOL_PERNODE: pidx = m->to_pool[cpu_to_node(cpu)]; break; } return &serv->sv_pools[pidx % serv->sv_nrpools]; } static int svc_rpcb_setup(struct svc_serv *serv, struct net *net) { int err; err = rpcb_create_local(net); if (err) return err; /* Remove any stale portmap registrations */ svc_unregister(serv, net); return 0; } void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net) { svc_unregister(serv, net); rpcb_put_local(net); } EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); static int svc_uses_rpcbind(struct svc_serv *serv) { unsigned int p, i; for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; if (!progp->pg_vers[i]->vs_hidden) return 1; } } return 0; } int svc_bind(struct svc_serv *serv, struct net *net) { if (!svc_uses_rpcbind(serv)) return 0; return svc_rpcb_setup(serv, net); } EXPORT_SYMBOL_GPL(svc_bind); #if defined(CONFIG_SUNRPC_BACKCHANNEL) static void __svc_init_bc(struct svc_serv *serv) { lwq_init(&serv->sv_cb_list); } #else static void __svc_init_bc(struct svc_serv *serv) { } #endif /* * Create an RPC service */ static struct svc_serv * __svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, unsigned int bufsize, int npools, int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int vers; unsigned int xdrsize; unsigned int i; if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; serv->sv_name = prog->pg_name; serv->sv_programs = prog; serv->sv_nprogs = nprogs; serv->sv_stats = stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; serv->sv_max_payload = bufsize? bufsize : 4096; serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); serv->sv_threadfn = threadfn; xdrsize = 0; for (i = 0; i < nprogs; i++) { struct svc_program *progp = &prog[i]; progp->pg_lovers = progp->pg_nvers-1; for (vers = 0; vers < progp->pg_nvers ; vers++) if (progp->pg_vers[vers]) { progp->pg_hivers = vers; if (progp->pg_lovers > vers) progp->pg_lovers = vers; if (progp->pg_vers[vers]->vs_xdrsize > xdrsize) xdrsize = progp->pg_vers[vers]->vs_xdrsize; } } serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); timer_setup(&serv->sv_temptimer, NULL, 0); spin_lock_init(&serv->sv_lock); __svc_init_bc(serv); serv->sv_nrpools = npools; serv->sv_pools = kcalloc(serv->sv_nrpools, sizeof(struct svc_pool), GFP_KERNEL); if (!serv->sv_pools) { kfree(serv); return NULL; } for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; dprintk("svc: initialising pool %u for %s\n", i, serv->sv_name); pool->sp_id = i; lwq_init(&pool->sp_xprts); INIT_LIST_HEAD(&pool->sp_all_threads); init_llist_head(&pool->sp_idle_threads); percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL); percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL); percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL); } return serv; } /** * svc_create - Create an RPC service * @prog: the RPC program the new service will handle * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog * * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, int (*threadfn)(void *data)) { return __svc_create(prog, 1, NULL, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); /** * svc_create_pooled - Create an RPC service with pooled threads * @prog: Array of RPC programs the new service will handle * @nprogs: Number of programs in the array * @stats: the stats struct if desired * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog * * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create_pooled(struct svc_program *prog, unsigned int nprogs, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn); if (!serv) goto out_err; serv->sv_is_pooled = true; return serv; out_err: svc_pool_map_put(); return NULL; } EXPORT_SYMBOL_GPL(svc_create_pooled); /* * Destroy an RPC service. Should be called with appropriate locking to * protect sv_permsocks and sv_tempsocks. */ void svc_destroy(struct svc_serv **servp) { struct svc_serv *serv = *servp; unsigned int i; *servp = NULL; dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name); timer_shutdown_sync(&serv->sv_temptimer); /* * Remaining transports at this point are not expected. */ WARN_ONCE(!list_empty(&serv->sv_permsocks), "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name); WARN_ONCE(!list_empty(&serv->sv_tempsocks), "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name); cache_clean_deferred(serv); if (serv->sv_is_pooled) svc_pool_map_put(); for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; percpu_counter_destroy(&pool->sp_messages_arrived); percpu_counter_destroy(&pool->sp_sockets_queued); percpu_counter_destroy(&pool->sp_threads_woken); } kfree(serv->sv_pools); kfree(serv); } EXPORT_SYMBOL_GPL(svc_destroy); static bool svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node) { rqstp->rq_maxpages = svc_serv_maxpages(serv); /* rq_pages' last entry is NULL for historical reasons. */ rqstp->rq_pages = kcalloc_node(rqstp->rq_maxpages + 1, sizeof(struct page *), GFP_KERNEL, node); if (!rqstp->rq_pages) return false; return true; } /* * Release an RPC server buffer */ static void svc_release_buffer(struct svc_rqst *rqstp) { unsigned long i; for (i = 0; i < rqstp->rq_maxpages; i++) if (rqstp->rq_pages[i]) put_page(rqstp->rq_pages[i]); kfree(rqstp->rq_pages); } static void svc_rqst_free(struct svc_rqst *rqstp) { folio_batch_release(&rqstp->rq_fbatch); kfree(rqstp->rq_bvec); svc_release_buffer(rqstp); if (rqstp->rq_scratch_page) put_page(rqstp->rq_scratch_page); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); kfree_rcu(rqstp, rq_rcu_head); } static struct svc_rqst * svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) return rqstp; folio_batch_init(&rqstp->rq_fbatch); rqstp->rq_server = serv; rqstp->rq_pool = pool; rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0); if (!rqstp->rq_scratch_page) goto out_enomem; rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) goto out_enomem; rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) goto out_enomem; if (!svc_init_buffer(rqstp, serv, node)) goto out_enomem; rqstp->rq_bvec = kcalloc_node(rqstp->rq_maxpages, sizeof(struct bio_vec), GFP_KERNEL, node); if (!rqstp->rq_bvec) goto out_enomem; rqstp->rq_err = -EAGAIN; /* No error yet */ serv->sv_nrthreads += 1; pool->sp_nrthreads += 1; /* Protected by whatever lock the service uses when calling * svc_set_num_threads() */ list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); return rqstp; out_enomem: svc_rqst_free(rqstp); return NULL; } /** * svc_pool_wake_idle_thread - Awaken an idle thread in @pool * @pool: service thread pool * * Can be called from soft IRQ or process context. Finding an idle * service thread and marking it BUSY is atomic with respect to * other calls to svc_pool_wake_idle_thread(). * */ void svc_pool_wake_idle_thread(struct svc_pool *pool) { struct svc_rqst *rqstp; struct llist_node *ln; rcu_read_lock(); ln = READ_ONCE(pool->sp_idle_threads.first); if (ln) { rqstp = llist_entry(ln, struct svc_rqst, rq_idle); WRITE_ONCE(rqstp->rq_qtime, ktime_get()); if (!task_is_running(rqstp->rq_task)) { wake_up_process(rqstp->rq_task); trace_svc_wake_up(rqstp->rq_task->pid); percpu_counter_inc(&pool->sp_threads_woken); } rcu_read_unlock(); return; } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(svc_pool_wake_idle_thread); static struct svc_pool * svc_pool_next(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) { return pool ? pool : &serv->sv_pools[(*state)++ % serv->sv_nrpools]; } static struct svc_pool * svc_pool_victim(struct svc_serv *serv, struct svc_pool *target_pool, unsigned int *state) { struct svc_pool *pool; unsigned int i; pool = target_pool; if (!pool) { for (i = 0; i < serv->sv_nrpools; i++) { pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; if (pool->sp_nrthreads) break; } } if (pool && pool->sp_nrthreads) { set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); set_bit(SP_NEED_VICTIM, &pool->sp_flags); return pool; } return NULL; } static int svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { struct svc_rqst *rqstp; struct task_struct *task; struct svc_pool *chosen_pool; unsigned int state = serv->sv_nrthreads-1; int node; int err; do { nrservs--; chosen_pool = svc_pool_next(serv, pool, &state); node = svc_pool_map_get_node(chosen_pool->sp_id); rqstp = svc_prepare_thread(serv, chosen_pool, node); if (!rqstp) return -ENOMEM; task = kthread_create_on_node(serv->sv_threadfn, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { svc_exit_thread(rqstp); return PTR_ERR(task); } rqstp->rq_task = task; if (serv->sv_nrpools > 1) svc_pool_map_set_cpumask(task, chosen_pool->sp_id); svc_sock_update_bufs(serv); wake_up_process(task); wait_var_event(&rqstp->rq_err, rqstp->rq_err != -EAGAIN); err = rqstp->rq_err; if (err) { svc_exit_thread(rqstp); return err; } } while (nrservs > 0); return 0; } static int svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { unsigned int state = serv->sv_nrthreads-1; struct svc_pool *victim; do { victim = svc_pool_victim(serv, pool, &state); if (!victim) break; svc_pool_wake_idle_thread(victim); wait_on_bit(&victim->sp_flags, SP_VICTIM_REMAINS, TASK_IDLE); nrservs++; } while (nrservs < 0); return 0; } /** * svc_set_num_threads - adjust number of threads per RPC service * @serv: RPC service to adjust * @pool: Specific pool from which to choose threads, or NULL * @nrservs: New number of threads for @serv (0 or less means kill all threads) * * Create or destroy threads to make the number of threads for @serv the * given number. If @pool is non-NULL, change only threads in that pool; * otherwise, round-robin between all pools for @serv. @serv's * sv_nrthreads is adjusted for each thread created or destroyed. * * Caller must ensure mutual exclusion between this and server startup or * shutdown. * * Returns zero on success or a negative errno if an error occurred while * starting a thread. */ int svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (!pool) nrservs -= serv->sv_nrthreads; else nrservs -= pool->sp_nrthreads; if (nrservs > 0) return svc_start_kthreads(serv, pool, nrservs); if (nrservs < 0) return svc_stop_kthreads(serv, pool, nrservs); return 0; } EXPORT_SYMBOL_GPL(svc_set_num_threads); /** * svc_rqst_replace_page - Replace one page in rq_pages[] * @rqstp: svc_rqst with pages to replace * @page: replacement page * * When replacing a page in rq_pages, batch the release of the * replaced pages to avoid hammering the page allocator. * * Return values: * %true: page replaced * %false: array bounds checking failed */ bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) { struct page **begin = rqstp->rq_pages; struct page **end = &rqstp->rq_pages[rqstp->rq_maxpages]; if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) { trace_svc_replace_page_err(rqstp); return false; } if (*rqstp->rq_next_page) { if (!folio_batch_add(&rqstp->rq_fbatch, page_folio(*rqstp->rq_next_page))) __folio_batch_release(&rqstp->rq_fbatch); } get_page(page); *(rqstp->rq_next_page++) = page; return true; } EXPORT_SYMBOL_GPL(svc_rqst_replace_page); /** * svc_rqst_release_pages - Release Reply buffer pages * @rqstp: RPC transaction context * * Release response pages that might still be in flight after * svc_send, and any spliced filesystem-owned pages. */ void svc_rqst_release_pages(struct svc_rqst *rqstp) { int i, count = rqstp->rq_next_page - rqstp->rq_respages; if (count) { release_pages(rqstp->rq_respages, count); for (i = 0; i < count; i++) rqstp->rq_respages[i] = NULL; } } /** * svc_exit_thread - finalise the termination of a sunrpc server thread * @rqstp: the svc_rqst which represents the thread. * * When a thread started with svc_new_thread() exits it must call * svc_exit_thread() as its last act. This must be done with the * service mutex held. Normally this is held by a DIFFERENT thread, the * one that is calling svc_set_num_threads() and which will wait for * SP_VICTIM_REMAINS to be cleared before dropping the mutex. If the * thread exits for any reason other than svc_thread_should_stop() * returning %true (which indicated that svc_set_num_threads() is * waiting for it to exit), then it must take the service mutex itself, * which can only safely be done using mutex_try_lock(). */ void svc_exit_thread(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct svc_pool *pool = rqstp->rq_pool; list_del_rcu(&rqstp->rq_all); pool->sp_nrthreads -= 1; serv->sv_nrthreads -= 1; svc_sock_update_bufs(serv); svc_rqst_free(rqstp); clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags); } EXPORT_SYMBOL_GPL(svc_exit_thread); /* * Register an "inet" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. * * No netconfig infrastructure is available in the kernel, so * we map IP_ protocol numbers to netids by hand. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_rpcb_register4(struct net *net, const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { const struct sockaddr_in sin = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; const char *netid; int error; switch (protocol) { case IPPROTO_UDP: netid = RPCBIND_NETID_UDP; break; case IPPROTO_TCP: netid = RPCBIND_NETID_TCP; break; default: return -ENOPROTOOPT; } error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin, netid); /* * User space didn't support rpcbind v4, so retry this * registration request with the legacy rpcbind v2 protocol. */ if (error == -EPROTONOSUPPORT) error = rpcb_register(net, program, version, protocol, port); return error; } #if IS_ENABLED(CONFIG_IPV6) /* * Register an "inet6" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. * * No netconfig infrastructure is available in the kernel, so * we map IP_ protocol numbers to netids by hand. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_rpcb_register6(struct net *net, const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { const struct sockaddr_in6 sin6 = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_ANY_INIT, .sin6_port = htons(port), }; const char *netid; int error; switch (protocol) { case IPPROTO_UDP: netid = RPCBIND_NETID_UDP6; break; case IPPROTO_TCP: netid = RPCBIND_NETID_TCP6; break; default: return -ENOPROTOOPT; } error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin6, netid); /* * User space didn't support rpcbind version 4, so we won't * use a PF_INET6 listener. */ if (error == -EPROTONOSUPPORT) error = -EAFNOSUPPORT; return error; } #endif /* IS_ENABLED(CONFIG_IPV6) */ /* * Register a kernel RPC service via rpcbind version 4. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_register(struct net *net, const char *progname, const u32 program, const u32 version, const int family, const unsigned short protocol, const unsigned short port) { int error = -EAFNOSUPPORT; switch (family) { case PF_INET: error = __svc_rpcb_register4(net, program, version, protocol, port); break; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: error = __svc_rpcb_register6(net, program, version, protocol, port); #endif } trace_svc_register(progname, version, family, protocol, port, error); return error; } static int svc_rpcbind_set_version(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { return __svc_register(net, progp->pg_name, progp->pg_prog, version, family, proto, port); } int svc_generic_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { const struct svc_version *vers = progp->pg_vers[version]; int error; if (vers == NULL) return 0; if (vers->vs_hidden) { trace_svc_noregister(progp->pg_name, version, proto, port, family, 0); return 0; } /* * Don't register a UDP port if we need congestion * control. */ if (vers->vs_need_cong_ctrl && proto == IPPROTO_UDP) return 0; error = svc_rpcbind_set_version(net, progp, version, family, proto, port); return (vers->vs_rpcb_optnl) ? 0 : error; } EXPORT_SYMBOL_GPL(svc_generic_rpcbind_set); /** * svc_register - register an RPC service with the local portmapper * @serv: svc_serv struct for the service to register * @net: net namespace for the service to register * @family: protocol family of service's listener socket * @proto: transport protocol number to advertise * @port: port to advertise * * Service is registered for any address in the passed-in protocol family */ int svc_register(const struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { unsigned int p, i; int error = 0; WARN_ON_ONCE(proto == 0 && port == 0); if (proto == 0 && port == 0) return -EINVAL; for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { error = progp->pg_rpcbind_set(net, progp, i, family, proto, port); if (error < 0) { printk(KERN_WARNING "svc: failed to register " "%sv%u RPC service (errno %d).\n", progp->pg_name, i, -error); break; } } } return error; } /* * If user space is running rpcbind, it should take the v4 UNSET * and clear everything for this [program, version]. If user space * is running portmap, it will reject the v4 UNSET, but won't have * any "inet6" entries anyway. So a PMAP_UNSET should be sufficient * in this case to clear all existing entries for [program, version]. */ static void __svc_unregister(struct net *net, const u32 program, const u32 version, const char *progname) { int error; error = rpcb_v4_register(net, program, version, NULL, ""); /* * User space didn't support rpcbind v4, so retry this * request with the legacy rpcbind v2 protocol. */ if (error == -EPROTONOSUPPORT) error = rpcb_register(net, program, version, 0, 0); trace_svc_unregister(progname, version, error); } /* * All netids, bind addresses and ports registered for [program, version] * are removed from the local rpcbind database (if the service is not * hidden) to make way for a new instance of the service. * * The result of unregistration is reported via dprintk for those who want * verification of the result, but is otherwise not important. */ static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct sighand_struct *sighand; unsigned long flags; unsigned int p, i; clear_thread_flag(TIF_SIGPENDING); for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; if (progp->pg_vers[i]->vs_hidden) continue; __svc_unregister(net, progp->pg_prog, i, progp->pg_name); } } rcu_read_lock(); sighand = rcu_dereference(current->sighand); spin_lock_irqsave(&sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(&sighand->siglock, flags); rcu_read_unlock(); } /* * dprintk the given error with the address of the client that caused it. */ #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { struct va_format vaf; va_list args; char buf[RPC_MAX_ADDRBUFLEN]; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); va_end(args); } #else static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif __be32 svc_generic_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { const struct svc_version *versp = NULL; /* compiler food */ const struct svc_procedure *procp = NULL; if (rqstp->rq_vers >= progp->pg_nvers ) goto err_bad_vers; versp = progp->pg_vers[rqstp->rq_vers]; if (!versp) goto err_bad_vers; /* * Some protocol versions (namely NFSv4) require some form of * congestion control. (See RFC 7530 section 3.1 paragraph 2) * In other words, UDP is not allowed. We mark those when setting * up the svc_xprt, and verify that here. * * The spec is not very clear about what error should be returned * when someone tries to access a server that is listening on UDP * for lower versions. RPC_PROG_MISMATCH seems to be the closest * fit. */ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt && !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags)) goto err_bad_vers; if (rqstp->rq_proc >= versp->vs_nproc) goto err_bad_proc; rqstp->rq_procinfo = procp = &versp->vs_proc[rqstp->rq_proc]; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argzero); memset(rqstp->rq_resp, 0, procp->pc_ressize); /* Bump per-procedure stats counter */ this_cpu_inc(versp->vs_count[rqstp->rq_proc]); ret->dispatch = versp->vs_dispatch; return rpc_success; err_bad_vers: ret->mismatch.lovers = progp->pg_lovers; ret->mismatch.hivers = progp->pg_hivers; return rpc_prog_mismatch; err_bad_proc: return rpc_proc_unavail; } EXPORT_SYMBOL_GPL(svc_generic_init_request); /* * Common routine for processing the RPC request. */ static int svc_process_common(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_res_stream; struct svc_program *progp = NULL; const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; struct svc_process_info process; enum svc_auth_status auth_res; unsigned int aoffset; int pr, rc; __be32 *p; /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); clear_bit(RQ_DROPME, &rqstp->rq_flags); /* Construct the first words of the reply: */ svcxdr_init_encode(rqstp); xdr_stream_encode_be32(xdr, rqstp->rq_xid); xdr_stream_encode_be32(xdr, rpc_reply); p = xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 4); if (unlikely(!p)) goto err_short_len; if (*p++ != cpu_to_be32(RPC_VERSION)) goto err_bad_rpc; xdr_stream_encode_be32(xdr, rpc_msg_accepted); rqstp->rq_prog = be32_to_cpup(p++); rqstp->rq_vers = be32_to_cpup(p++); rqstp->rq_proc = be32_to_cpup(p); for (pr = 0; pr < serv->sv_nprogs; pr++) if (rqstp->rq_prog == serv->sv_programs[pr].pg_prog) progp = &serv->sv_programs[pr]; /* * Decode auth data, and add verifier to reply buffer. * We do this before anything else in order to get a decent * auth verifier. */ auth_res = svc_authenticate(rqstp); /* Also give the program a chance to reject this call: */ if (auth_res == SVC_OK && progp) auth_res = progp->pg_authenticate(rqstp); trace_svc_authenticate(rqstp, auth_res); switch (auth_res) { case SVC_OK: break; case SVC_GARBAGE: rqstp->rq_auth_stat = rpc_autherr_badcred; goto err_bad_auth; case SVC_SYSERR: goto err_system_err; case SVC_DENIED: goto err_bad_auth; case SVC_CLOSE: goto close; case SVC_DROP: goto dropit; case SVC_COMPLETE: goto sendit; default: pr_warn_once("Unexpected svc_auth_status (%d)\n", auth_res); goto err_system_err; } if (progp == NULL) goto err_bad_prog; switch (progp->pg_init_request(rqstp, progp, &process)) { case rpc_success: break; case rpc_prog_unavail: goto err_bad_prog; case rpc_prog_mismatch: goto err_bad_vers; case rpc_proc_unavail: goto err_bad_proc; } procp = rqstp->rq_procinfo; /* Should this check go into the dispatcher? */ if (!procp || !procp->pc_func) goto err_bad_proc; /* Syntactic check complete */ if (serv->sv_stats) serv->sv_stats->rpccnt++; trace_svc_process(rqstp, progp->pg_name); aoffset = xdr_stream_pos(xdr); /* un-reserve some of the out-queue now that we have a * better idea of reply size */ if (procp->pc_xdrressize) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); /* Call the function that processes the request. */ rc = process.dispatch(rqstp); if (procp->pc_release) procp->pc_release(rqstp); xdr_finish_decode(xdr); if (!rc) goto dropit; if (rqstp->rq_auth_stat != rpc_auth_ok) goto err_bad_auth; if (*rqstp->rq_accept_statp != rpc_success) xdr_truncate_encode(xdr, aoffset); if (procp->pc_encode == NULL) goto dropit; sendit: if (svc_authorise(rqstp)) goto close_xprt; return 1; /* Caller can now send it */ dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); return 0; close: svc_authorise(rqstp); close_xprt: if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_xprt_close(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); return 0; err_short_len: svc_printk(rqstp, "short len %u, dropping request\n", rqstp->rq_arg.len); goto close_xprt; err_bad_rpc: if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; xdr_stream_encode_u32(xdr, RPC_MSG_DENIED); xdr_stream_encode_u32(xdr, RPC_MISMATCH); /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", be32_to_cpu(rqstp->rq_auth_stat)); if (serv->sv_stats) serv->sv_stats->rpcbadauth++; /* Restore write pointer to location of reply status: */ xdr_truncate_encode(xdr, XDR_UNIT * 2); xdr_stream_encode_u32(xdr, RPC_MSG_DENIED); xdr_stream_encode_u32(xdr, RPC_AUTH_ERROR); xdr_stream_encode_be32(xdr, rqstp->rq_auth_stat); goto sendit; err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: svc_printk(rqstp, "unknown version (%d for prog %d, %s)\n", rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_prog_mismatch; /* * svc_authenticate() has already added the verifier and * advanced the stream just past rq_accept_statp. */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; err_bad_proc: svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_system_err: if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } /* * Drop request */ static void svc_drop(struct svc_rqst *rqstp) { trace_svc_drop(rqstp); } /** * svc_process - Execute one RPC transaction * @rqstp: RPC transaction context * */ void svc_process(struct svc_rqst *rqstp) { struct kvec *resv = &rqstp->rq_res.head[0]; __be32 *p; #if IS_ENABLED(CONFIG_FAIL_SUNRPC) if (!fail_sunrpc.ignore_server_disconnect && should_fail(&fail_sunrpc.attr, 1)) svc_xprt_deferred_close(rqstp->rq_xprt); #endif /* * Setup response xdr_buf. * Initially it has just one page */ rqstp->rq_next_page = &rqstp->rq_respages[1]; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; rqstp->rq_res.pages = rqstp->rq_next_page; rqstp->rq_res.len = 0; rqstp->rq_res.page_base = 0; rqstp->rq_res.page_len = 0; rqstp->rq_res.buflen = PAGE_SIZE; rqstp->rq_res.tail[0].iov_base = NULL; rqstp->rq_res.tail[0].iov_len = 0; svcxdr_init_decode(rqstp); p = xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 2); if (unlikely(!p)) goto out_drop; rqstp->rq_xid = *p++; if (unlikely(*p != rpc_call)) goto out_baddir; if (!svc_process_common(rqstp)) goto out_drop; svc_send(rqstp); return; out_baddir: svc_printk(rqstp, "bad direction 0x%08x, dropping request\n", be32_to_cpu(*p)); if (rqstp->rq_server->sv_stats) rqstp->rq_server->sv_stats->rpcbadfmt++; out_drop: svc_drop(rqstp); } #if defined(CONFIG_SUNRPC_BACKCHANNEL) /** * svc_process_bc - process a reverse-direction RPC request * @req: RPC request to be used for client-side processing * @rqstp: server-side execution context * */ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) { struct rpc_timeout timeout = { .to_increment = 0, }; struct rpc_task *task; int proc_error; /* Build the svc_rqst used by the common processing routine */ rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_bc_net = req->rq_xprt->xprt_net; rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg)); memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res)); /* Adjust the argument buffer length */ rqstp->rq_arg.len = req->rq_private_buf.len; if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; rqstp->rq_arg.page_len = 0; } else if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len) rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; else rqstp->rq_arg.len = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len; /* Reset the response buffer */ rqstp->rq_res.head[0].iov_len = 0; /* * Skip the XID and calldir fields because they've already * been processed by the caller. */ svcxdr_init_decode(rqstp); if (!xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 2)) return; /* Parse and execute the bc call */ proc_error = svc_process_common(rqstp); atomic_dec(&req->rq_xprt->bc_slot_count); if (!proc_error) { /* Processing error: drop the request */ xprt_free_bc_request(req); return; } /* Finally, send the reply synchronously */ if (rqstp->bc_to_initval > 0) { timeout.to_initval = rqstp->bc_to_initval; timeout.to_retries = rqstp->bc_to_retries; } else { timeout.to_initval = req->rq_xprt->timeout->to_initval; timeout.to_retries = req->rq_xprt->timeout->to_retries; } timeout.to_maxval = timeout.to_initval; memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); task = rpc_run_bc_task(req, &timeout); if (IS_ERR(task)) return; WARN_ON_ONCE(atomic_read(&task->tk_count) != 1); rpc_put_task(task); } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** * svc_max_payload - Return transport-specific limit on the RPC payload * @rqstp: RPC transaction context * * Returns the maximum number of payload bytes the current transport * allows. */ u32 svc_max_payload(const struct svc_rqst *rqstp) { u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload; if (rqstp->rq_server->sv_max_payload < max) max = rqstp->rq_server->sv_max_payload; return max; } EXPORT_SYMBOL_GPL(svc_max_payload); /** * svc_proc_name - Return RPC procedure name in string form * @rqstp: svc_rqst to operate on * * Return value: * Pointer to a NUL-terminated string */ const char *svc_proc_name(const struct svc_rqst *rqstp) { if (rqstp && rqstp->rq_procinfo) return rqstp->rq_procinfo->pc_name; return "unknown"; } /** * svc_encode_result_payload - mark a range of bytes as a result payload * @rqstp: svc_rqst to operate on * @offset: payload's byte offset in rqstp->rq_res * @length: size of payload, in bytes * * Returns zero on success, or a negative errno if a permanent * error occurred. */ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length) { return rqstp->rq_xprt->xpt_ops->xpo_result_payload(rqstp, offset, length); } EXPORT_SYMBOL_GPL(svc_encode_result_payload); /** * svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call * @rqstp: svc_rqst to operate on * @first: buffer containing first section of pathname * @p: buffer containing remaining section of pathname * @total: total length of the pathname argument * * The VFS symlink API demands a NUL-terminated pathname in mapped memory. * Returns pointer to a NUL-terminated string, or an ERR_PTR. Caller must free * the returned string. */ char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total) { size_t len, remaining; char *result, *dst; result = kmalloc(total + 1, GFP_KERNEL); if (!result) return ERR_PTR(-ESERVERFAULT); dst = result; remaining = total; len = min_t(size_t, total, first->iov_len); if (len) { memcpy(dst, first->iov_base, len); dst += len; remaining -= len; } if (remaining) { len = min_t(size_t, remaining, PAGE_SIZE); memcpy(dst, p, len); dst += len; } *dst = '\0'; /* Sanity check: Linux doesn't allow the pathname argument to * contain a NUL byte. */ if (strlen(result) != total) { kfree(result); return ERR_PTR(-EINVAL); } return result; } EXPORT_SYMBOL_GPL(svc_fill_symlink_pathname); |
| 87 77 54 54 87 79 78 79 79 89 87 77 8 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Serge Hallyn <serue@us.ibm.com> * Reiner Sailer <sailer@watson.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_queue.c * Implements queues that store template measurements and * maintains aggregate over the stored measurements * in the pre-configured TPM PCR (if available). * The measurement list is append-only. No entry is * ever removed or changed during the boot-cycle. */ #include <linux/rculist.h> #include <linux/reboot.h> #include <linux/slab.h> #include "ima.h" #define AUDIT_CAUSE_LEN_MAX 32 /* pre-allocated array of tpm_digest structures to extend a PCR */ static struct tpm_digest *digests; LIST_HEAD(ima_measurements); /* list of all measurements */ #ifdef CONFIG_IMA_KEXEC static unsigned long binary_runtime_size; #else static unsigned long binary_runtime_size = ULONG_MAX; #endif /* key: inode (before secure-hashing a file) */ struct ima_h_table ima_htable = { .len = ATOMIC_LONG_INIT(0), .violations = ATOMIC_LONG_INIT(0), .queue[0 ... IMA_MEASURE_HTABLE_SIZE - 1] = HLIST_HEAD_INIT }; /* mutex protects atomicity of extending measurement list * and extending the TPM PCR aggregate. Since tpm_extend can take * long (and the tpm driver uses a mutex), we can't use the spinlock. */ static DEFINE_MUTEX(ima_extend_list_mutex); /* * Used internally by the kernel to suspend measurements. * Protected by ima_extend_list_mutex. */ static bool ima_measurements_suspended; /* lookup up the digest value in the hash table, and return the entry */ static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value, int pcr) { struct ima_queue_entry *qe, *ret = NULL; unsigned int key; int rc; key = ima_hash_key(digest_value); rcu_read_lock(); hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) { rc = memcmp(qe->entry->digests[ima_hash_algo_idx].digest, digest_value, hash_digest_size[ima_hash_algo]); if ((rc == 0) && (qe->entry->pcr == pcr)) { ret = qe; break; } } rcu_read_unlock(); return ret; } /* * Calculate the memory required for serializing a single * binary_runtime_measurement list entry, which contains a * couple of variable length fields (e.g template name and data). */ static int get_binary_runtime_size(struct ima_template_entry *entry) { int size = 0; size += sizeof(u32); /* pcr */ size += TPM_DIGEST_SIZE; size += sizeof(int); /* template name size field */ size += strlen(entry->template_desc->name); size += sizeof(entry->template_data_len); size += entry->template_data_len; return size; } /* ima_add_template_entry helper function: * - Add template entry to the measurement list and hash table, for * all entries except those carried across kexec. * * (Called with ima_extend_list_mutex held.) */ static int ima_add_digest_entry(struct ima_template_entry *entry, bool update_htable) { struct ima_queue_entry *qe; unsigned int key; qe = kmalloc(sizeof(*qe), GFP_KERNEL); if (qe == NULL) { pr_err("OUT OF MEMORY ERROR creating queue entry\n"); return -ENOMEM; } qe->entry = entry; INIT_LIST_HEAD(&qe->later); list_add_tail_rcu(&qe->later, &ima_measurements); atomic_long_inc(&ima_htable.len); if (update_htable) { key = ima_hash_key(entry->digests[ima_hash_algo_idx].digest); hlist_add_head_rcu(&qe->hnext, &ima_htable.queue[key]); } if (binary_runtime_size != ULONG_MAX) { int size; size = get_binary_runtime_size(entry); binary_runtime_size = (binary_runtime_size < ULONG_MAX - size) ? binary_runtime_size + size : ULONG_MAX; } return 0; } /* * Return the amount of memory required for serializing the * entire binary_runtime_measurement list, including the ima_kexec_hdr * structure. */ unsigned long ima_get_binary_runtime_size(void) { if (binary_runtime_size >= (ULONG_MAX - sizeof(struct ima_kexec_hdr))) return ULONG_MAX; else return binary_runtime_size + sizeof(struct ima_kexec_hdr); } static int ima_pcr_extend(struct tpm_digest *digests_arg, int pcr) { int result = 0; if (!ima_tpm_chip) return result; result = tpm_pcr_extend(ima_tpm_chip, pcr, digests_arg); if (result != 0) pr_err("Error Communicating to TPM chip, result: %d\n", result); return result; } /* * Add template entry to the measurement list and hash table, and * extend the pcr. * * On systems which support carrying the IMA measurement list across * kexec, maintain the total memory size required for serializing the * binary_runtime_measurements. */ int ima_add_template_entry(struct ima_template_entry *entry, int violation, const char *op, struct inode *inode, const unsigned char *filename) { u8 *digest = entry->digests[ima_hash_algo_idx].digest; struct tpm_digest *digests_arg = entry->digests; const char *audit_cause = "hash_added"; char tpm_audit_cause[AUDIT_CAUSE_LEN_MAX]; int audit_info = 1; int result = 0, tpmresult = 0; mutex_lock(&ima_extend_list_mutex); /* * Avoid appending to the measurement log when the TPM subsystem has * been shut down while preparing for system reboot. */ if (ima_measurements_suspended) { audit_cause = "measurements_suspended"; audit_info = 0; result = -ENODEV; goto out; } if (!violation && !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) { if (ima_lookup_digest_entry(digest, entry->pcr)) { audit_cause = "hash_exists"; result = -EEXIST; goto out; } } result = ima_add_digest_entry(entry, !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)); if (result < 0) { audit_cause = "ENOMEM"; audit_info = 0; goto out; } if (violation) /* invalidate pcr */ digests_arg = digests; tpmresult = ima_pcr_extend(digests_arg, entry->pcr); if (tpmresult != 0) { snprintf(tpm_audit_cause, AUDIT_CAUSE_LEN_MAX, "TPM_error(%d)", tpmresult); audit_cause = tpm_audit_cause; audit_info = 0; } out: mutex_unlock(&ima_extend_list_mutex); integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename, op, audit_cause, result, audit_info); return result; } int ima_restore_measurement_entry(struct ima_template_entry *entry) { int result = 0; mutex_lock(&ima_extend_list_mutex); result = ima_add_digest_entry(entry, 0); mutex_unlock(&ima_extend_list_mutex); return result; } static void ima_measurements_suspend(void) { mutex_lock(&ima_extend_list_mutex); ima_measurements_suspended = true; mutex_unlock(&ima_extend_list_mutex); } static int ima_reboot_notifier(struct notifier_block *nb, unsigned long action, void *data) { #ifdef CONFIG_IMA_KEXEC if (action == SYS_RESTART && data && !strcmp(data, "kexec reboot")) ima_measure_kexec_event("kexec_execute"); #endif ima_measurements_suspend(); return NOTIFY_DONE; } static struct notifier_block ima_reboot_nb = { .notifier_call = ima_reboot_notifier, }; void __init ima_init_reboot_notifier(void) { register_reboot_notifier(&ima_reboot_nb); } int __init ima_init_digests(void) { u16 digest_size; u16 crypto_id; int i; if (!ima_tpm_chip) return 0; digests = kcalloc(ima_tpm_chip->nr_allocated_banks, sizeof(*digests), GFP_NOFS); if (!digests) return -ENOMEM; for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) { digests[i].alg_id = ima_tpm_chip->allocated_banks[i].alg_id; digest_size = ima_tpm_chip->allocated_banks[i].digest_size; crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id; /* for unmapped TPM algorithms digest is still a padded SHA1 */ if (crypto_id == HASH_ALGO__LAST) digest_size = SHA1_DIGEST_SIZE; memset(digests[i].digest, 0xff, digest_size); } return 0; } |
| 20 20 20 20 20 76 20 68 51 499 20 20 20 20 20 20 20 20 20 20 20 20 609 604 4 4 4 221 254 392 609 1 333 412 802 393 609 778 916 919 99 804 20 20 20 20 20 20 20 33 12 7 40 29 35 7 36 36 6 6 6 40 36 6 23 47 40 23 20 20 20 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 | /* * Copyright (c) 2018 Cumulus Networks. All rights reserved. * Copyright (c) 2018 David Ahern <dsa@cumulusnetworks.com> * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this * source tree. * * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ #include <linux/bitmap.h> #include <linux/in6.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rhashtable.h> #include <linux/spinlock_types.h> #include <linux/types.h> #include <net/fib_notifier.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/fib_rules.h> #include <net/net_namespace.h> #include <net/nexthop.h> #include <linux/debugfs.h> #include "netdevsim.h" struct nsim_fib_entry { u64 max; atomic64_t num; }; struct nsim_per_fib_data { struct nsim_fib_entry fib; struct nsim_fib_entry rules; }; struct nsim_fib_data { struct notifier_block fib_nb; struct nsim_per_fib_data ipv4; struct nsim_per_fib_data ipv6; struct nsim_fib_entry nexthops; struct rhashtable fib_rt_ht; struct list_head fib_rt_list; struct mutex fib_lock; /* Protects FIB HT and list */ struct notifier_block nexthop_nb; struct rhashtable nexthop_ht; struct devlink *devlink; struct work_struct fib_event_work; struct work_struct fib_flush_work; struct list_head fib_event_queue; spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ struct mutex nh_lock; /* Protects NH HT */ struct dentry *ddir; bool fail_route_offload; bool fail_res_nexthop_group_replace; bool fail_nexthop_bucket_replace; bool fail_route_delete; }; struct nsim_fib_rt_key { unsigned char addr[sizeof(struct in6_addr)]; unsigned char prefix_len; int family; u32 tb_id; }; struct nsim_fib_rt { struct nsim_fib_rt_key key; struct rhash_head ht_node; struct list_head list; /* Member of fib_rt_list */ }; struct nsim_fib4_rt { struct nsim_fib_rt common; struct fib_info *fi; dscp_t dscp; u8 type; }; struct nsim_fib6_rt { struct nsim_fib_rt common; struct list_head nh_list; unsigned int nhs; }; struct nsim_fib6_rt_nh { struct list_head list; /* Member of nh_list */ struct fib6_info *rt; }; struct nsim_fib6_event { struct fib6_info **rt_arr; unsigned int nrt6; }; struct nsim_fib_event { struct list_head list; /* node in fib queue */ union { struct fib_entry_notifier_info fen_info; struct nsim_fib6_event fib6_event; }; struct nsim_fib_data *data; unsigned long event; int family; }; static const struct rhashtable_params nsim_fib_rt_ht_params = { .key_offset = offsetof(struct nsim_fib_rt, key), .head_offset = offsetof(struct nsim_fib_rt, ht_node), .key_len = sizeof(struct nsim_fib_rt_key), .automatic_shrinking = true, }; struct nsim_nexthop { struct rhash_head ht_node; u64 occ; u32 id; bool is_resilient; }; static const struct rhashtable_params nsim_nexthop_ht_params = { .key_offset = offsetof(struct nsim_nexthop, id), .head_offset = offsetof(struct nsim_nexthop, ht_node), .key_len = sizeof(u32), .automatic_shrinking = true, }; u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max) { struct nsim_fib_entry *entry; switch (res_id) { case NSIM_RESOURCE_IPV4_FIB: entry = &fib_data->ipv4.fib; break; case NSIM_RESOURCE_IPV4_FIB_RULES: entry = &fib_data->ipv4.rules; break; case NSIM_RESOURCE_IPV6_FIB: entry = &fib_data->ipv6.fib; break; case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; case NSIM_RESOURCE_NEXTHOPS: entry = &fib_data->nexthops; break; default: return 0; } return max ? entry->max : atomic64_read(&entry->num); } static void nsim_fib_set_max(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, u64 val) { struct nsim_fib_entry *entry; switch (res_id) { case NSIM_RESOURCE_IPV4_FIB: entry = &fib_data->ipv4.fib; break; case NSIM_RESOURCE_IPV4_FIB_RULES: entry = &fib_data->ipv4.rules; break; case NSIM_RESOURCE_IPV6_FIB: entry = &fib_data->ipv6.fib; break; case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; case NSIM_RESOURCE_NEXTHOPS: entry = &fib_data->nexthops; break; default: WARN_ON(1); return; } entry->max = val; } static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, struct netlink_ext_ack *extack) { int err = 0; if (add) { if (!atomic64_add_unless(&entry->num, 1, entry->max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries"); } } else { atomic64_dec_if_positive(&entry->num); } return err; } static int nsim_fib_rule_event(struct nsim_fib_data *data, struct fib_notifier_info *info, bool add) { struct netlink_ext_ack *extack = info->extack; int err = 0; switch (info->family) { case AF_INET: err = nsim_fib_rule_account(&data->ipv4.rules, add, extack); break; case AF_INET6: err = nsim_fib_rule_account(&data->ipv6.rules, add, extack); break; } return err; } static int nsim_fib_account(struct nsim_fib_entry *entry, bool add) { int err = 0; if (add) { if (!atomic64_add_unless(&entry->num, 1, entry->max)) err = -ENOSPC; } else { atomic64_dec_if_positive(&entry->num); } return err; } static void nsim_fib_rt_init(struct nsim_fib_data *data, struct nsim_fib_rt *fib_rt, const void *addr, size_t addr_len, unsigned int prefix_len, int family, u32 tb_id) { memcpy(fib_rt->key.addr, addr, addr_len); fib_rt->key.prefix_len = prefix_len; fib_rt->key.family = family; fib_rt->key.tb_id = tb_id; list_add(&fib_rt->list, &data->fib_rt_list); } static void nsim_fib_rt_fini(struct nsim_fib_rt *fib_rt) { list_del(&fib_rt->list); } static struct nsim_fib_rt *nsim_fib_rt_lookup(struct rhashtable *fib_rt_ht, const void *addr, size_t addr_len, unsigned int prefix_len, int family, u32 tb_id) { struct nsim_fib_rt_key key; memset(&key, 0, sizeof(key)); memcpy(key.addr, addr, addr_len); key.prefix_len = prefix_len; key.family = family; key.tb_id = tb_id; return rhashtable_lookup_fast(fib_rt_ht, &key, nsim_fib_rt_ht_params); } static struct nsim_fib4_rt * nsim_fib4_rt_create(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt; fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_KERNEL); if (!fib4_rt) return NULL; nsim_fib_rt_init(data, &fib4_rt->common, &fen_info->dst, sizeof(u32), fen_info->dst_len, AF_INET, fen_info->tb_id); fib4_rt->fi = fen_info->fi; fib_info_hold(fib4_rt->fi); fib4_rt->dscp = fen_info->dscp; fib4_rt->type = fen_info->type; return fib4_rt; } static void nsim_fib4_rt_destroy(struct nsim_fib4_rt *fib4_rt) { fib_info_put(fib4_rt->fi); nsim_fib_rt_fini(&fib4_rt->common); kfree(fib4_rt); } static struct nsim_fib4_rt * nsim_fib4_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib_entry_notifier_info *fen_info) { struct nsim_fib_rt *fib_rt; fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &fen_info->dst, sizeof(u32), fen_info->dst_len, AF_INET, fen_info->tb_id); if (!fib_rt) return NULL; return container_of(fib_rt, struct nsim_fib4_rt, common); } static void nsim_fib4_rt_offload_failed_flag_set(struct net *net, struct fib_entry_notifier_info *fen_info) { u32 *p_dst = (u32 *)&fen_info->dst; struct fib_rt_info fri; fri.fi = fen_info->fi; fri.tb_id = fen_info->tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = fen_info->dst_len; fri.dscp = fen_info->dscp; fri.type = fen_info->type; fri.offload = false; fri.trap = false; fri.offload_failed = true; fib_alias_hw_flags_set(net, &fri); } static void nsim_fib4_rt_hw_flags_set(struct net *net, const struct nsim_fib4_rt *fib4_rt, bool trap) { u32 *p_dst = (u32 *) fib4_rt->common.key.addr; int dst_len = fib4_rt->common.key.prefix_len; struct fib_rt_info fri; fri.fi = fib4_rt->fi; fri.tb_id = fib4_rt->common.key.tb_id; fri.dst = cpu_to_be32(*p_dst); fri.dst_len = dst_len; fri.dscp = fib4_rt->dscp; fri.type = fib4_rt->type; fri.offload = false; fri.trap = trap; fri.offload_failed = false; fib_alias_hw_flags_set(net, &fri); } static int nsim_fib4_rt_add(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt) { struct net *net = devlink_net(data->devlink); int err; err = rhashtable_insert_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) goto err_fib_dismiss; /* Simulate hardware programming latency. */ msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); return 0; err_fib_dismiss: /* Drop the accounting that was increased from the notification * context when FIB_EVENT_ENTRY_REPLACE was triggered. */ nsim_fib_account(&data->ipv4.fib, false); return err; } static int nsim_fib4_rt_replace(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt, struct nsim_fib4_rt *fib4_rt_old) { struct net *net = devlink_net(data->devlink); int err; /* We are replacing a route, so need to remove the accounting which * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. */ err = nsim_fib_account(&data->ipv4.fib, false); if (err) return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib4_rt_old->common.ht_node, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) return err; msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false); nsim_fib4_rt_destroy(fib4_rt_old); return 0; } static int nsim_fib4_rt_insert(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt, *fib4_rt_old; int err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib4_rt = nsim_fib4_rt_create(data, fen_info); if (!fib4_rt) return -ENOMEM; fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt_old) err = nsim_fib4_rt_add(data, fib4_rt); else err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old); if (err) nsim_fib4_rt_destroy(fib4_rt); return err; } static void nsim_fib4_rt_remove(struct nsim_fib_data *data, const struct fib_entry_notifier_info *fen_info) { struct nsim_fib4_rt *fib4_rt; fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt) return; rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); nsim_fib4_rt_destroy(fib4_rt); } static int nsim_fib4_event(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info, unsigned long event) { int err = 0; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib4_rt_insert(data, fen_info); if (err) { struct net *net = devlink_net(data->devlink); nsim_fib4_rt_offload_failed_flag_set(net, fen_info); } break; case FIB_EVENT_ENTRY_DEL: nsim_fib4_rt_remove(data, fen_info); break; default: break; } return err; } static struct nsim_fib6_rt_nh * nsim_fib6_rt_nh_find(const struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) { if (fib6_rt_nh->rt == rt) return fib6_rt_nh; } return NULL; } static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_KERNEL); if (!fib6_rt_nh) return -ENOMEM; fib6_info_hold(rt); fib6_rt_nh->rt = rt; list_add_tail(&fib6_rt_nh->list, &fib6_rt->nh_list); fib6_rt->nhs++; return 0; } #if IS_ENABLED(CONFIG_IPV6) static void nsim_rt6_release(struct fib6_info *rt) { fib6_info_release(rt); } #else static void nsim_rt6_release(struct fib6_info *rt) { } #endif static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { struct nsim_fib6_rt_nh *fib6_rt_nh; fib6_rt_nh = nsim_fib6_rt_nh_find(fib6_rt, rt); if (!fib6_rt_nh) return; fib6_rt->nhs--; list_del(&fib6_rt_nh->list); nsim_rt6_release(fib6_rt_nh->rt); kfree(fib6_rt_nh); } static struct nsim_fib6_rt * nsim_fib6_rt_create(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { struct fib6_info *rt = rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i = 0; int err; fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_KERNEL); if (!fib6_rt) return ERR_PTR(-ENOMEM); nsim_fib_rt_init(data, &fib6_rt->common, &rt->fib6_dst.addr, sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6, rt->fib6_table->tb6_id); /* We consider a multipath IPv6 route as one entry, but it can be made * up from several fib6_info structs (one for each nexthop), so we * add them all to the same list under the entry. */ INIT_LIST_HEAD(&fib6_rt->nh_list); for (i = 0; i < nrt6; i++) { err = nsim_fib6_rt_nh_add(fib6_rt, rt_arr[i]); if (err) goto err_fib6_rt_nh_del; } return fib6_rt; err_fib6_rt_nh_del: for (i--; i >= 0; i--) { nsim_fib6_rt_nh_del(fib6_rt, rt_arr[i]); } nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); return ERR_PTR(err); } static void nsim_fib6_rt_destroy(struct nsim_fib6_rt *fib6_rt) { struct nsim_fib6_rt_nh *iter, *tmp; list_for_each_entry_safe(iter, tmp, &fib6_rt->nh_list, list) nsim_fib6_rt_nh_del(fib6_rt, iter->rt); WARN_ON_ONCE(!list_empty(&fib6_rt->nh_list)); nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); } static struct nsim_fib6_rt * nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt) { struct nsim_fib_rt *fib_rt; fib_rt = nsim_fib_rt_lookup(fib_rt_ht, &rt->fib6_dst.addr, sizeof(rt->fib6_dst.addr), rt->fib6_dst.plen, AF_INET6, rt->fib6_table->tb6_id); if (!fib_rt) return NULL; return container_of(fib_rt, struct nsim_fib6_rt, common); } static int nsim_fib6_rt_append(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i, err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return -EINVAL; for (i = 0; i < fib6_event->nrt6; i++) { err = nsim_fib6_rt_nh_add(fib6_rt, fib6_event->rt_arr[i]); if (err) goto err_fib6_rt_nh_del; WRITE_ONCE(fib6_event->rt_arr[i]->trap, true); } return 0; err_fib6_rt_nh_del: for (i--; i >= 0; i--) { WRITE_ONCE(fib6_event->rt_arr[i]->trap, false); nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); } return err; } #if IS_ENABLED(CONFIG_IPV6) static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { struct net *net = devlink_net(data->devlink); int i; for (i = 0; i < nrt6; i++) fib6_info_hw_flags_set(net, rt_arr[i], false, false, true); } #else static void nsim_fib6_rt_offload_failed_flag_set(struct nsim_fib_data *data, struct fib6_info **rt_arr, unsigned int nrt6) { } #endif #if IS_ENABLED(CONFIG_IPV6) static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, const struct nsim_fib6_rt *fib6_rt, bool trap) { struct net *net = devlink_net(data->devlink); struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap, false); } #else static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, const struct nsim_fib6_rt *fib6_rt, bool trap) { } #endif static int nsim_fib6_rt_add(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt) { int err; err = rhashtable_insert_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) goto err_fib_dismiss; msleep(1); nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); return 0; err_fib_dismiss: /* Drop the accounting that was increased from the notification * context when FIB_EVENT_ENTRY_REPLACE was triggered. */ nsim_fib_account(&data->ipv6.fib, false); return err; } static int nsim_fib6_rt_replace(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt, struct nsim_fib6_rt *fib6_rt_old) { int err; /* We are replacing a route, so need to remove the accounting which * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. */ err = nsim_fib_account(&data->ipv6.fib, false); if (err) return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib6_rt_old->common.ht_node, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); if (err) return err; msleep(1); nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); nsim_fib6_rt_hw_flags_set(data, fib6_rt_old, false); nsim_fib6_rt_destroy(fib6_rt_old); return 0; } static int nsim_fib6_rt_insert(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt, *fib6_rt_old; int err; if (data->fail_route_offload) { /* For testing purposes, user set debugfs fail_route_offload * value to true. Simulate hardware programming latency and then * fail. */ msleep(1); return -EINVAL; } fib6_rt = nsim_fib6_rt_create(data, fib6_event->rt_arr, fib6_event->nrt6); if (IS_ERR(fib6_rt)) return PTR_ERR(fib6_rt); fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt_old) err = nsim_fib6_rt_add(data, fib6_rt); else err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old); if (err) nsim_fib6_rt_destroy(fib6_rt); return err; } static void nsim_fib6_rt_remove(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event) { struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete * notification for a route we do not have. Therefore, do not warn if * route was not found. */ fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ if (fib6_event->nrt6 != fib6_rt->nhs) { for (i = 0; i < fib6_event->nrt6; i++) nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); return; } rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); nsim_fib6_rt_destroy(fib6_rt); } static int nsim_fib6_event_init(struct nsim_fib6_event *fib6_event, struct fib6_entry_notifier_info *fen6_info) { struct fib6_info *rt = fen6_info->rt; struct fib6_info **rt_arr; struct fib6_info *iter; unsigned int nrt6; int i = 0; nrt6 = fen6_info->nsiblings + 1; rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC); if (!rt_arr) return -ENOMEM; fib6_event->rt_arr = rt_arr; fib6_event->nrt6 = nrt6; rt_arr[0] = rt; fib6_info_hold(rt); if (!fen6_info->nsiblings) return 0; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (i == fen6_info->nsiblings) break; rt_arr[i + 1] = iter; fib6_info_hold(iter); i++; } WARN_ON_ONCE(i != fen6_info->nsiblings); return 0; } static void nsim_fib6_event_fini(struct nsim_fib6_event *fib6_event) { int i; for (i = 0; i < fib6_event->nrt6; i++) nsim_rt6_release(fib6_event->rt_arr[i]); kfree(fib6_event->rt_arr); } static int nsim_fib6_event(struct nsim_fib_data *data, struct nsim_fib6_event *fib6_event, unsigned long event) { int err; if (fib6_event->rt_arr[0]->fib6_src.plen) return 0; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib6_rt_insert(data, fib6_event); if (err) goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_APPEND: err = nsim_fib6_rt_append(data, fib6_event); if (err) goto err_rt_offload_failed_flag_set; break; case FIB_EVENT_ENTRY_DEL: nsim_fib6_rt_remove(data, fib6_event); break; default: break; } return 0; err_rt_offload_failed_flag_set: nsim_fib6_rt_offload_failed_flag_set(data, fib6_event->rt_arr, fib6_event->nrt6); return err; } static void nsim_fib_event(struct nsim_fib_event *fib_event) { switch (fib_event->family) { case AF_INET: nsim_fib4_event(fib_event->data, &fib_event->fen_info, fib_event->event); fib_info_put(fib_event->fen_info.fi); break; case AF_INET6: nsim_fib6_event(fib_event->data, &fib_event->fib6_event, fib_event->event); nsim_fib6_event_fini(&fib_event->fib6_event); break; } } static int nsim_fib4_prepare_event(struct fib_notifier_info *info, struct nsim_fib_event *fib_event, unsigned long event) { struct nsim_fib_data *data = fib_event->data; struct fib_entry_notifier_info *fen_info; struct netlink_ext_ack *extack; int err = 0; fen_info = container_of(info, struct fib_entry_notifier_info, info); fib_event->fen_info = *fen_info; extack = info->extack; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib_account(&data->ipv4.fib, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); return err; } break; case FIB_EVENT_ENTRY_DEL: if (data->fail_route_delete) { NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); return -EINVAL; } nsim_fib_account(&data->ipv4.fib, false); break; } /* Take reference on fib_info to prevent it from being * freed while event is queued. Release it afterwards. */ fib_info_hold(fib_event->fen_info.fi); return 0; } static int nsim_fib6_prepare_event(struct fib_notifier_info *info, struct nsim_fib_event *fib_event, unsigned long event) { struct nsim_fib_data *data = fib_event->data; struct fib6_entry_notifier_info *fen6_info; struct netlink_ext_ack *extack; int err = 0; fen6_info = container_of(info, struct fib6_entry_notifier_info, info); err = nsim_fib6_event_init(&fib_event->fib6_event, fen6_info); if (err) return err; extack = info->extack; switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib_account(&data->ipv6.fib, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); goto err_fib6_event_fini; } break; case FIB_EVENT_ENTRY_DEL: if (data->fail_route_delete) { err = -EINVAL; NL_SET_ERR_MSG_MOD(extack, "Failed to process route deletion"); goto err_fib6_event_fini; } nsim_fib_account(&data->ipv6.fib, false); break; } return 0; err_fib6_event_fini: nsim_fib6_event_fini(&fib_event->fib6_event); return err; } static int nsim_fib_event_schedule_work(struct nsim_fib_data *data, struct fib_notifier_info *info, unsigned long event) { struct nsim_fib_event *fib_event; int err; if (info->family != AF_INET && info->family != AF_INET6) /* netdevsim does not support 'RTNL_FAMILY_IP6MR' and * 'RTNL_FAMILY_IPMR' and should ignore them. */ return NOTIFY_DONE; fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); if (!fib_event) goto err_fib_event_alloc; fib_event->data = data; fib_event->event = event; fib_event->family = info->family; switch (info->family) { case AF_INET: err = nsim_fib4_prepare_event(info, fib_event, event); break; case AF_INET6: err = nsim_fib6_prepare_event(info, fib_event, event); break; } if (err) goto err_fib_prepare_event; /* Enqueue the event and trigger the work */ spin_lock_bh(&data->fib_event_queue_lock); list_add_tail(&fib_event->list, &data->fib_event_queue); spin_unlock_bh(&data->fib_event_queue_lock); schedule_work(&data->fib_event_work); return NOTIFY_DONE; err_fib_prepare_event: kfree(fib_event); err_fib_event_alloc: if (event == FIB_EVENT_ENTRY_DEL) schedule_work(&data->fib_flush_work); return NOTIFY_BAD; } static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct fib_notifier_info *info = ptr; int err; switch (event) { case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = nsim_fib_rule_event(data, info, event == FIB_EVENT_RULE_ADD); return notifier_from_errno(err); case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: return nsim_fib_event_schedule_work(data, info, event); } return NOTIFY_DONE; } static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib_data *data) { struct devlink *devlink = data->devlink; struct nsim_fib4_rt *fib4_rt; fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common); nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false); nsim_fib_account(&data->ipv4.fib, false); nsim_fib4_rt_destroy(fib4_rt); } static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib_data *data) { struct nsim_fib6_rt *fib6_rt; fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common); nsim_fib6_rt_hw_flags_set(data, fib6_rt, false); nsim_fib_account(&data->ipv6.fib, false); nsim_fib6_rt_destroy(fib6_rt); } static void nsim_fib_rt_free(void *ptr, void *arg) { struct nsim_fib_rt *fib_rt = ptr; struct nsim_fib_data *data = arg; switch (fib_rt->key.family) { case AF_INET: nsim_fib4_rt_free(fib_rt, data); break; case AF_INET6: nsim_fib6_rt_free(fib_rt, data); break; default: WARN_ON_ONCE(1); } } /* inconsistent dump, trying again */ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; /* Flush the work to make sure there is no race with notifications. */ flush_work(&data->fib_event_work); /* The notifier block is still not registered, so we do not need to * take any locks here. */ list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) { rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node, nsim_fib_rt_ht_params); nsim_fib_rt_free(fib_rt, data); } atomic64_set(&data->ipv4.rules.num, 0ULL); atomic64_set(&data->ipv6.rules.num, 0ULL); } static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop; u64 occ = 0; int i; nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL); if (!nexthop) return ERR_PTR(-ENOMEM); nexthop->id = info->id; /* Determine the number of nexthop entries the new nexthop will * occupy. */ switch (info->type) { case NH_NOTIFIER_INFO_TYPE_SINGLE: occ = 1; break; case NH_NOTIFIER_INFO_TYPE_GRP: for (i = 0; i < info->nh_grp->num_nh; i++) occ += info->nh_grp->nh_entries[i].weight; break; case NH_NOTIFIER_INFO_TYPE_RES_TABLE: occ = info->nh_res_table->num_nh_buckets; nexthop->is_resilient = true; break; default: NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type"); kfree(nexthop); return ERR_PTR(-EOPNOTSUPP); } nexthop->occ = occ; return nexthop; } static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop) { kfree(nexthop); } static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ, bool add, struct netlink_ext_ack *extack) { int i, err = 0; if (add) { for (i = 0; i < occ; i++) if (!atomic64_add_unless(&data->nexthops.num, 1, data->nexthops.max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); goto err_num_decrease; } } else { if (WARN_ON(occ > atomic64_read(&data->nexthops.num))) return -EINVAL; atomic64_sub(occ, &data->nexthops.num); } return err; err_num_decrease: atomic64_sub(i, &data->nexthops.num); return err; } static void nsim_nexthop_hw_flags_set(struct net *net, const struct nsim_nexthop *nexthop, bool trap) { int i; nexthop_set_hw_flags(net, nexthop->id, false, trap); if (!nexthop->is_resilient) return; for (i = 0; i < nexthop->occ; i++) nexthop_bucket_set_hw_flags(net, nexthop->id, i, false, trap); } static int nsim_nexthop_add(struct nsim_fib_data *data, struct nsim_nexthop *nexthop, struct netlink_ext_ack *extack) { struct net *net = devlink_net(data->devlink); int err; err = nsim_nexthop_account(data, nexthop->occ, true, extack); if (err) return err; err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node, nsim_nexthop_ht_params); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop"); goto err_nexthop_dismiss; } nsim_nexthop_hw_flags_set(net, nexthop, true); return 0; err_nexthop_dismiss: nsim_nexthop_account(data, nexthop->occ, false, extack); return err; } static int nsim_nexthop_replace(struct nsim_fib_data *data, struct nsim_nexthop *nexthop, struct nsim_nexthop *nexthop_old, struct netlink_ext_ack *extack) { struct net *net = devlink_net(data->devlink); int err; err = nsim_nexthop_account(data, nexthop->occ, true, extack); if (err) return err; err = rhashtable_replace_fast(&data->nexthop_ht, &nexthop_old->ht_node, &nexthop->ht_node, nsim_nexthop_ht_params); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop"); goto err_nexthop_dismiss; } nsim_nexthop_hw_flags_set(net, nexthop, true); nsim_nexthop_account(data, nexthop_old->occ, false, extack); nsim_nexthop_destroy(nexthop_old); return 0; err_nexthop_dismiss: nsim_nexthop_account(data, nexthop->occ, false, extack); return err; } static int nsim_nexthop_insert(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop, *nexthop_old; int err; nexthop = nsim_nexthop_create(data, info); if (IS_ERR(nexthop)) return PTR_ERR(nexthop); nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, nsim_nexthop_ht_params); if (!nexthop_old) err = nsim_nexthop_add(data, nexthop, info->extack); else err = nsim_nexthop_replace(data, nexthop, nexthop_old, info->extack); if (err) nsim_nexthop_destroy(nexthop); return err; } static void nsim_nexthop_remove(struct nsim_fib_data *data, struct nh_notifier_info *info) { struct nsim_nexthop *nexthop; nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, nsim_nexthop_ht_params); if (!nexthop) return; rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node, nsim_nexthop_ht_params); nsim_nexthop_account(data, nexthop->occ, false, info->extack); nsim_nexthop_destroy(nexthop); } static int nsim_nexthop_res_table_pre_replace(struct nsim_fib_data *data, struct nh_notifier_info *info) { if (data->fail_res_nexthop_group_replace) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace a resilient nexthop group"); return -EINVAL; } return 0; } static int nsim_nexthop_bucket_replace(struct nsim_fib_data *data, struct nh_notifier_info *info) { if (data->fail_nexthop_bucket_replace) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to replace nexthop bucket"); return -EINVAL; } nexthop_bucket_set_hw_flags(info->net, info->id, info->nh_res_bucket->bucket_index, false, true); return 0; } static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, nexthop_nb); struct nh_notifier_info *info = ptr; int err = 0; mutex_lock(&data->nh_lock); switch (event) { case NEXTHOP_EVENT_REPLACE: err = nsim_nexthop_insert(data, info); break; case NEXTHOP_EVENT_DEL: nsim_nexthop_remove(data, info); break; case NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE: err = nsim_nexthop_res_table_pre_replace(data, info); break; case NEXTHOP_EVENT_BUCKET_REPLACE: err = nsim_nexthop_bucket_replace(data, info); break; default: break; } mutex_unlock(&data->nh_lock); return notifier_from_errno(err); } static void nsim_nexthop_free(void *ptr, void *arg) { struct nsim_nexthop *nexthop = ptr; struct nsim_fib_data *data = arg; struct net *net; net = devlink_net(data->devlink); nsim_nexthop_hw_flags_set(net, nexthop, false); nsim_nexthop_account(data, nexthop->occ, false, NULL); nsim_nexthop_destroy(nexthop); } static ssize_t nsim_nexthop_bucket_activity_write(struct file *file, const char __user *user_buf, size_t size, loff_t *ppos) { struct nsim_fib_data *data = file->private_data; struct net *net = devlink_net(data->devlink); struct nsim_nexthop *nexthop; unsigned long *activity; loff_t pos = *ppos; u16 bucket_index; char buf[128]; int err = 0; u32 nhid; if (pos != 0) return -EINVAL; if (size > sizeof(buf) - 1) return -EINVAL; if (copy_from_user(buf, user_buf, size)) return -EFAULT; buf[size] = 0; if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2) return -EINVAL; rtnl_lock(); nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &nhid, nsim_nexthop_ht_params); if (!nexthop || !nexthop->is_resilient || bucket_index >= nexthop->occ) { err = -EINVAL; goto out; } activity = bitmap_zalloc(nexthop->occ, GFP_KERNEL); if (!activity) { err = -ENOMEM; goto out; } bitmap_set(activity, bucket_index, 1); nexthop_res_grp_activity_update(net, nhid, nexthop->occ, activity); bitmap_free(activity); out: rtnl_unlock(); *ppos = size; return err ?: size; } static const struct file_operations nsim_nexthop_bucket_activity_fops = { .open = simple_open, .write = nsim_nexthop_bucket_activity_write, .owner = THIS_MODULE, }; static u64 nsim_fib_ipv4_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB, false); } static u64 nsim_fib_ipv4_rules_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV4_FIB_RULES, false); } static u64 nsim_fib_ipv6_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB, false); } static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false); } static u64 nsim_fib_nexthops_res_occ_get(void *priv) { struct nsim_fib_data *data = priv; return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false); } static void nsim_fib_set_max_all(struct nsim_fib_data *data, struct devlink *devlink) { static const enum nsim_resource_id res_ids[] = { NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, NSIM_RESOURCE_NEXTHOPS, }; int i; for (i = 0; i < ARRAY_SIZE(res_ids); i++) { int err; u64 val; err = devl_resource_size_get(devlink, res_ids[i], &val); if (err) val = (u64) -1; nsim_fib_set_max(data, res_ids[i], val); } } static void nsim_fib_event_work(struct work_struct *work) { struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, fib_event_work); struct nsim_fib_event *fib_event, *next_fib_event; LIST_HEAD(fib_event_queue); spin_lock_bh(&data->fib_event_queue_lock); list_splice_init(&data->fib_event_queue, &fib_event_queue); spin_unlock_bh(&data->fib_event_queue_lock); mutex_lock(&data->fib_lock); list_for_each_entry_safe(fib_event, next_fib_event, &fib_event_queue, list) { nsim_fib_event(fib_event); list_del(&fib_event->list); kfree(fib_event); cond_resched(); } mutex_unlock(&data->fib_lock); } static void nsim_fib_flush_work(struct work_struct *work) { struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, fib_flush_work); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; /* Process pending work. */ flush_work(&data->fib_event_work); mutex_lock(&data->fib_lock); list_for_each_entry_safe(fib_rt, fib_rt_tmp, &data->fib_rt_list, list) { rhashtable_remove_fast(&data->fib_rt_ht, &fib_rt->ht_node, nsim_fib_rt_ht_params); nsim_fib_rt_free(fib_rt, data); } mutex_unlock(&data->fib_lock); } static int nsim_fib_debugfs_init(struct nsim_fib_data *data, struct nsim_dev *nsim_dev) { data->ddir = debugfs_create_dir("fib", nsim_dev->ddir); if (IS_ERR(data->ddir)) return PTR_ERR(data->ddir); data->fail_route_offload = false; debugfs_create_bool("fail_route_offload", 0600, data->ddir, &data->fail_route_offload); data->fail_res_nexthop_group_replace = false; debugfs_create_bool("fail_res_nexthop_group_replace", 0600, data->ddir, &data->fail_res_nexthop_group_replace); data->fail_nexthop_bucket_replace = false; debugfs_create_bool("fail_nexthop_bucket_replace", 0600, data->ddir, &data->fail_nexthop_bucket_replace); debugfs_create_file("nexthop_bucket_activity", 0200, data->ddir, data, &nsim_nexthop_bucket_activity_fops); data->fail_route_delete = false; debugfs_create_bool("fail_route_delete", 0600, data->ddir, &data->fail_route_delete); return 0; } static void nsim_fib_debugfs_exit(struct nsim_fib_data *data) { debugfs_remove_recursive(data->ddir); } struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, struct netlink_ext_ack *extack) { struct nsim_fib_data *data; struct nsim_dev *nsim_dev; int err; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); data->devlink = devlink; nsim_dev = devlink_priv(devlink); err = nsim_fib_debugfs_init(data, nsim_dev); if (err) goto err_data_free; mutex_init(&data->nh_lock); err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params); if (err) goto err_debugfs_exit; mutex_init(&data->fib_lock); INIT_LIST_HEAD(&data->fib_rt_list); err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params); if (err) goto err_rhashtable_nexthop_destroy; INIT_WORK(&data->fib_event_work, nsim_fib_event_work); INIT_WORK(&data->fib_flush_work, nsim_fib_flush_work); INIT_LIST_HEAD(&data->fib_event_queue); spin_lock_init(&data->fib_event_queue_lock); nsim_fib_set_max_all(data, devlink); data->nexthop_nb.notifier_call = nsim_nexthop_event_nb; err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb, extack); if (err) { pr_err("Failed to register nexthop notifier\n"); goto err_rhashtable_fib_destroy; } data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(devlink_net(devlink), &data->fib_nb, nsim_fib_dump_inconsistent, extack); if (err) { pr_err("Failed to register fib notifier\n"); goto err_nexthop_nb_unregister; } devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV4_FIB, nsim_fib_ipv4_resource_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV4_FIB_RULES, nsim_fib_ipv4_rules_res_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV6_FIB, nsim_fib_ipv6_resource_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_IPV6_FIB_RULES, nsim_fib_ipv6_rules_res_occ_get, data); devl_resource_occ_get_register(devlink, NSIM_RESOURCE_NEXTHOPS, nsim_fib_nexthops_res_occ_get, data); return data; err_nexthop_nb_unregister: unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); err_rhashtable_fib_destroy: cancel_work_sync(&data->fib_flush_work); flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); err_rhashtable_nexthop_destroy: rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); mutex_destroy(&data->fib_lock); err_debugfs_exit: mutex_destroy(&data->nh_lock); nsim_fib_debugfs_exit(data); err_data_free: kfree(data); return ERR_PTR(err); } void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) { devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_NEXTHOPS); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB_RULES); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB_RULES); devl_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB); unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); cancel_work_sync(&data->fib_flush_work); flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); WARN_ON_ONCE(!list_empty(&data->fib_event_queue)); WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); mutex_destroy(&data->fib_lock); mutex_destroy(&data->nh_lock); nsim_fib_debugfs_exit(data); kfree(data); } |
| 9 10 4 4 4 3 1 8 8 8 7 1 7 7 7 6 1 16 7 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | // SPDX-License-Identifier: GPL-2.0-only /* * Transparent proxy support for Linux/iptables * * Copyright (C) 2007-2008 BalaBit IT Ltd. * Author: Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> #include <net/sock.h> #include <net/inet_sock.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/inet6_hashtables.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/netfilter/nf_socket.h> #include <linux/netfilter/xt_socket.h> /* "socket" match based redirection (no specific rule) * =================================================== * * There are connections with dynamic endpoints (e.g. FTP data * connection) that the user is unable to add explicit rules * for. These are taken care of by a generic "socket" rule. It is * assumed that the proxy application is trusted to open such * connections without explicit iptables rule (except of course the * generic 'socket' rule). In this case the following sockets are * matched in preference order: * * - match: if there's a fully established connection matching the * _packet_ tuple * * - match: if there's a non-zero bound listener (possibly with a * non-local address) We don't accept zero-bound listeners, since * then local services could intercept traffic going through the * box. */ static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { static struct xt_socket_mtinfo1 xt_info_v0 = { .flags = 0, }; return socket_match(skb, par, &xt_info_v0); } static bool socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { return socket_match(skb, par, par->matchinfo); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static bool socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); if (sk) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk_fullsock(sk) && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; } return sk != NULL; } #endif static int socket_mt_enable_defrag(struct net *net, int family) { switch (family) { case NFPROTO_IPV4: return nf_defrag_ipv4_enable(net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: return nf_defrag_ipv6_enable(net); #endif } WARN_ONCE(1, "Unknown family %d\n", family); return 0; } static int socket_mt_v1_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V1) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1); return -EINVAL; } return 0; } static int socket_mt_v2_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V2) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2); return -EINVAL; } return 0; } static int socket_mt_v3_check(const struct xt_mtchk_param *par) { const struct xt_socket_mtinfo3 *info = (struct xt_socket_mtinfo3 *)par->matchinfo; int err; err = socket_mt_enable_defrag(par->net, par->family); if (err) return err; if (info->flags & ~XT_SOCKET_FLAGS_V3) { pr_info_ratelimited("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V3); return -EINVAL; } return 0; } static void socket_mt_destroy(const struct xt_mtdtor_param *par) { if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) else if (par->family == NFPROTO_IPV6) nf_defrag_ipv6_disable(par->net); #endif } static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", .revision = 0, .family = NFPROTO_IPV4, .match = socket_mt4_v0, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { .name = "socket", .revision = 1, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .destroy = socket_mt_destroy, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 1, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .destroy = socket_mt_destroy, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 2, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 2, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v2_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif { .name = "socket", .revision = 3, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "socket", .revision = 3, .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v3_check, .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, #endif }; static int __init socket_mt_init(void) { return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } static void __exit socket_mt_exit(void) { xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } module_init(socket_mt_init); module_exit(socket_mt_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); MODULE_DESCRIPTION("x_tables socket match module"); MODULE_ALIAS("ipt_socket"); MODULE_ALIAS("ip6t_socket"); |
| 1 4 5 5 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Syncookies implementation for the Linux kernel * * Copyright (C) 1997 Andi Kleen * Based on ideas by D.J.Bernstein and Eric Schenk. */ #include <linux/tcp.h> #include <linux/siphash.h> #include <linux/kernel.h> #include <linux/export.h> #include <net/secure_seq.h> #include <net/tcp.h> #include <net/route.h> static siphash_aligned_key_t syncookie_secret[2]; #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) /* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK * stores TCP options: * * MSB LSB * | 31 ... 6 | 5 | 4 | 3 2 1 0 | * | Timestamp | ECN | SACK | WScale | * * When we receive a valid cookie-ACK, we look at the echoed tsval (if * any) to figure out which TCP options we should use for the rebuilt * connection. * * A WScale setting of '0xf' (which is an invalid scaling value) * means that original syn did not include the TCP window scaling option. */ #define TS_OPT_WSCALE_MASK 0xf #define TS_OPT_SACK BIT(4) #define TS_OPT_ECN BIT(5) /* There is no TS_OPT_TIMESTAMP: * if ACK contains timestamp option, we already know it was * requested/supported by the syn/synack exchange. */ #define TSBITS 6 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) { net_get_random_once(syncookie_secret, sizeof(syncookie_secret)); return siphash_4u32((__force u32)saddr, (__force u32)daddr, (__force u32)sport << 16 | (__force u32)dport, count, &syncookie_secret[c]); } /* * when syncookies are in effect and tcp timestamps are enabled we encode * tcp options in the lower bits of the timestamp value that will be * sent in the syn-ack. * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ u64 cookie_init_timestamp(struct request_sock *req, u64 now) { const struct inet_request_sock *ireq = inet_rsk(req); u64 ts, ts_now = tcp_ns_to_ts(false, now); u32 options = 0; options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK; if (ireq->sack_ok) options |= TS_OPT_SACK; if (ireq->ecn_ok) options |= TS_OPT_ECN; ts = (ts_now >> TSBITS) << TSBITS; ts |= options; if (ts > ts_now) ts -= (1UL << TSBITS); if (tcp_rsk(req)->req_usec_ts) return ts * NSEC_PER_USEC; return ts * NSEC_PER_MSEC; } static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, __u32 sseq, __u32 data) { /* * Compute the secure sequence number. * The output should be: * HASH(sec1,saddr,sport,daddr,dport,sec1) + sseq + (count * 2^24) * + (HASH(sec2,saddr,sport,daddr,dport,count,sec2) % 2^24). * Where sseq is their sequence number and count increases every * minute by 1. * As an extra hack, we add a small "data" value that encodes the * MSS into the second hash value. */ u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) & COOKIEMASK)); } /* * This retrieves the small "data" value from the syncookie. * If the syncookie is bad, the data returned will be out of * range. This must be checked by the caller. * * The count value used to generate the cookie must be less than * MAX_SYNCOOKIE_AGE minutes in the past. * The return value (__u32)-1 if this test fails. */ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr, __be16 sport, __be16 dport, __u32 sseq) { u32 diff, count = tcp_cookie_time(); /* Strip away the layers from the cookie */ cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; /* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */ diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - cookie_hash(saddr, daddr, sport, dport, count - diff, 1)) & COOKIEMASK; /* Leaving the data behind */ } /* * MSS Values are chosen based on the 2011 paper * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson. * Values .. * .. lower than 536 are rare (< 0.2%) * .. between 537 and 1299 account for less than < 1.5% of observed values * .. in the 1300-1349 range account for about 15 to 20% of observed mss values * .. exceeding 1460 are very rare (< 0.04%) * * 1460 is the single most frequently announced mss value (30 to 46% depending * on monitor location). Table must be sorted. */ static __u16 const msstab[] = { 536, 1300, 1440, /* 1440, 1452: PPPoE */ 1460, }; /* * Generate a syncookie. mssp points to the mss, which is returned * rounded down to the value encoded in the cookie. */ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp) { int mssind; const __u16 mss = *mssp; for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) if (mss >= msstab[mssind]) break; *mssp = msstab[mssind]; return secure_tcp_syn_cookie(iph->saddr, iph->daddr, th->source, th->dest, ntohl(th->seq), mssind); } EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); return __cookie_v4_init_sequence(iph, th, mssp); } /* * Check if a ack sequence number is a valid syncookie. * Return the decoded mss if it is, or 0 if not. */ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th) { __u32 cookie = ntohl(th->ack_seq) - 1; __u32 seq = ntohl(th->seq) - 1; __u32 mssind; mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr, th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } EXPORT_SYMBOL_GPL(__cookie_v4_check); struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; bool own_req; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, NULL, &own_req); if (child) { refcount_set(&req->rsk_refcnt, 1); sock_rps_save_rxhash(child, skb); if (rsk_drop_req(req)) { reqsk_put(req); return child; } if (inet_csk_reqsk_queue_add(sk, req, child)) return child; bh_unlock_sock(child); sock_put(child); } __reqsk_free(req); return NULL; } EXPORT_IPV6_MOD(tcp_get_cookie_sock); /* * when syncookies are in effect and tcp timestamps are enabled we stored * additional tcp options in the timestamp. * This extracts these options from the timestamp echo. * * return false if we decode a tcp option that is disabled * on the host. */ bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *tcp_opt) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr; if (!tcp_opt->saw_tstamp) { tcp_clear_options(tcp_opt); return true; } if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) return true; /* no window scaling */ tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } EXPORT_IPV6_MOD(cookie_timestamp_decode); static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); const struct tcphdr *th = tcp_hdr(skb); req->num_retrans = 0; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); ireq->ir_mark = inet_request_mark(sk, skb); if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; treq->snt_synack = 0; treq->snt_tsval_first = 0; treq->tfo_listener = false; treq->txhash = net_tx_rndhash(); treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = ntohl(th->ack_seq) - 1; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; treq->req_usec_ts = false; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) return mptcp_subflow_init_cookie_req(req, sk, skb); #endif return 0; } #if IS_ENABLED(CONFIG_BPF) struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) { struct request_sock *req = inet_reqsk(skb->sk); skb->sk = NULL; skb->destructor = NULL; if (cookie_tcp_reqsk_init(sk, skb, req)) { reqsk_free(req); req = NULL; } return req; } EXPORT_IPV6_MOD_GPL(cookie_bpf_check); #endif struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, int mss, u32 tsoff) { struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; if (sk_is_mptcp(sk)) req = mptcp_subflow_reqsk_alloc(ops, sk, false); else req = inet_reqsk_alloc(ops, sk, false); if (!req) return NULL; if (cookie_tcp_reqsk_init(sk, skb, req)) { reqsk_free(req); return NULL; } ireq = inet_rsk(req); treq = tcp_rsk(req); req->mss = mss; req->ts_recent = tcp_opt->saw_tstamp ? tcp_opt->rcv_tsval : 0; ireq->snd_wscale = tcp_opt->snd_wscale; ireq->tstamp_ok = tcp_opt->saw_tstamp; ireq->sack_ok = tcp_opt->sack_ok; ireq->wscale_ok = tcp_opt->wscale_ok; ireq->ecn_ok = !!(tcp_opt->rcv_tsecr & TS_OPT_ECN); treq->ts_off = tsoff; return req; } EXPORT_IPV6_MOD_GPL(cookie_tcp_reqsk_alloc); static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; u32 tsoff = 0; int mss; if (tcp_synq_no_recent_overflow(sk)) goto out; mss = __cookie_v4_check(ip_hdr(skb), tcp_hdr(skb)); if (!mss) { __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); goto out; } __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { tsoff = secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); tcp_opt.rcv_tsecr -= tsoff; } if (!cookie_timestamp_decode(net, &tcp_opt)) goto out; return cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb, &tcp_opt, mss, tsoff); out: return ERR_PTR(-EINVAL); } /* On input, sk is a listener. * Output is listener if incoming packet would not create a child * NULL if memory could not be allocated. */ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; const struct tcphdr *th = tcp_hdr(skb); struct tcp_sock *tp = tcp_sk(sk); struct inet_request_sock *ireq; struct net *net = sock_net(sk); struct request_sock *req; struct sock *ret = sk; struct flowi4 fl4; struct rtable *rt; __u8 rcv_wscale; int full_space; SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; if (cookie_bpf_ok(skb)) { req = cookie_bpf_check(sk, skb); } else { req = cookie_tcp_check(net, sk, skb); if (IS_ERR(req)) goto out; } if (!req) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } ireq = inet_rsk(req); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); if (security_inet_conn_request(sk, skb, req)) { SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; } tcp_ao_syncookie(sk, skb, req, AF_INET); /* * We need to lookup the route here to get at the correct * window size. We should better make sure that the window size * hasn't changed since we received the original syn, but I see * no easy way to do this. */ flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, th->source, th->dest, sk_uid(sk)); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; } /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? : dst_metric(&rt->dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); /* req->syncookie is set true only if ACK is validated * by BPF kfunc, then, rcv_wscale is already configured. */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ if (!ret) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } inet_sk(ret)->cork.fl.u.ip4 = fl4; out: return ret; out_free: reqsk_free(req); out_drop: sk_skb_reason_drop(sk, skb, reason); return NULL; } |
| 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the ICMP module. * * Version: @(#)icmp.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _ICMP_H #define _ICMP_H #include <linux/icmp.h> #include <net/inet_sock.h> #include <net/snmp.h> #include <net/ip.h> struct icmp_err { int errno; unsigned int fatal:1; }; extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define __ICMP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) #define ICMPMSGIN_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; struct sk_buff; struct net; void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct ip_options *opt); static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt); } #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct ip_options opts = { 0 }; __icmp_send(skb_in, type, code, info, &opts); } #endif int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ |
| 62 4 20 20 20 20 20 19 20 20 20 20 20 21 17 20 20 11 71 75 75 75 53 53 53 53 40 52 52 43 37 4 74 75 16 43 75 74 75 74 59 75 34 53 33 10 53 10 53 53 52 53 20 53 53 27 27 4 4 4 3 3 3 20 20 83 59 84 82 59 84 21 21 21 21 21 20 21 21 21 19 19 19 21 19 19 19 19 19 19 19 19 19 19 21 21 21 2 21 21 2189 2146 19 21 21 59 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @lock: protects all fields * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct work_struct work; struct net_device *dev; struct mutex lock; u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; queue_work(udp_tunnel_nic_workqueue, &utn->work); utn->work_pending = 1; } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; utn = dev->udp_tunnel_nic; if (!utn) return; mutex_lock(&utn->lock); utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release utn lock across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); mutex_unlock(&utn->lock); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void __udp_tunnel_nic_assert_locked(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) lockdep_assert_held(&utn->lock); } static void __udp_tunnel_nic_lock(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) mutex_lock(&utn->lock); } static void __udp_tunnel_nic_unlock(struct net_device *dev) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (utn) mutex_unlock(&utn->lock); } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, .assert_locked = __udp_tunnel_nic_assert_locked, .lock = __udp_tunnel_nic_lock, .unlock = __udp_tunnel_nic_unlock, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); mutex_lock(&utn->lock); utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); mutex_unlock(&utn->lock); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); mutex_init(&utn->lock); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) { udp_tunnel_nic_lock(dev); udp_tunnel_get_rx_info(dev); udp_tunnel_nic_unlock(dev); } return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; udp_tunnel_nic_lock(dev); /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) { udp_tunnel_nic_unlock(dev); return; } list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; udp_tunnel_nic_unlock(dev); goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); udp_tunnel_nic_unlock(dev); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. */ if (utn->work_pending) return; udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { udp_tunnel_nic_lock(dev); WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_lock(dev); udp_tunnel_nic_flush(dev, utn); udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL"); |
| 28 32 32 3 31 25 25 32 32 31 1 1 31 29 2 28 3 29 2 29 2 28 3 29 2 26 5 28 3 29 2 27 4 22 9 23 4 4 28 3 29 2 27 4 27 4 28 3 31 3 1 1 1 2 1 1 3 2 1 1 3 3 2 2 2 2 2 2 6 5 1 1 1 1 21 14 11 1 12 68 26 13 33 4 1 1 2 1 2 1 2 2 1 45 13 43 38 1 3 2 39 1 5 38 37 2 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ #include "netlink.h" #include "main.h" #include <linux/array_size.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/types.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" #include "log.h" #include "mesh-interface.h" #include "multicast.h" #include "network-coding.h" #include "originator.h" #include "tp_meter.h" #include "translation-table.h" struct genl_family batadv_netlink_family; /* multicast groups */ enum batadv_netlink_multicast_groups { BATADV_NL_MCGRP_CONFIG, BATADV_NL_MCGRP_TPMETER, }; /** * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags */ enum batadv_genl_ops_flags { /** * @BATADV_FLAG_NEED_MESH: request requires valid mesh interface in * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[0] */ BATADV_FLAG_NEED_MESH = BIT(0), /** * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_HARDIF = BIT(1), /** * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in * attribute BATADV_ATTR_VLANID and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_VLAN = BIT(2), }; static const struct genl_multicast_group batadv_netlink_mcgrps[] = { [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG }, [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_VERSION] = { .type = NLA_STRING }, [BATADV_ATTR_ALGO_NAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_MESH_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_HARD_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_HARD_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_HARD_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_ORIG_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TPMETER_RESULT] = { .type = NLA_U8 }, [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 }, [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, [BATADV_ATTR_TT_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TT_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_LAST_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_CRC32] = { .type = NLA_U32 }, [BATADV_ATTR_TT_VID] = { .type = NLA_U16 }, [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TQ] = { .type = NLA_U8 }, [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_OWN] = { .type = NLA_FLAG }, [BATADV_ATTR_BLA_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_VID] = { .type = NLA_U16 }, [BATADV_ATTR_BLA_BACKBONE] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_CRC] = { .type = NLA_U16 }, [BATADV_ATTR_DAT_CACHE_IP4ADDRESS] = { .type = NLA_U32 }, [BATADV_ATTR_DAT_CACHE_HWADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 }, [BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 }, [BATADV_ATTR_VLANID] = { .type = NLA_U16 }, [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_AP_ISOLATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ISOLATION_MARK] = { .type = NLA_U32 }, [BATADV_ATTR_ISOLATION_MASK] = { .type = NLA_U32 }, [BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_GW_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_GW_MODE] = { .type = NLA_U8 }, [BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 }, [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 }, [BATADV_ATTR_LOG_LEVEL] = { .type = NLA_U32 }, [BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_MULTICAST_FANOUT] = { .type = NLA_U32 }, [BATADV_ATTR_NETWORK_CODING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ORIG_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_ELP_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_THROUGHPUT_OVERRIDE] = { .type = NLA_U32 }, }; /** * batadv_netlink_get_ifindex() - Extract an interface index from a message * @nlh: Message header * @attrtype: Attribute which holds an interface index * * Return: interface index, or 0. */ static int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); return (attr && nla_len(attr) == sizeof(u32)) ? nla_get_u32(attr) : 0; } /** * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation meshif attribute * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, struct batadv_priv *bat_priv) { struct batadv_meshif_vlan *vlan; u8 ap_isolation; vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return 0; ap_isolation = atomic_read(&vlan->ap_isolation); batadv_meshif_vlan_put(vlan); return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!ap_isolation); } /** * batadv_netlink_set_mesh_ap_isolation() - Set ap_isolation from genl msg * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr, struct batadv_priv *bat_priv) { struct batadv_meshif_vlan *vlan; vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return -ENOENT; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); batadv_meshif_vlan_put(vlan); return 0; } /** * batadv_netlink_mesh_fill() - Fill message with mesh attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the mesh interface information * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { struct net_device *mesh_iface = bat_priv->mesh_iface; struct batadv_hard_iface *primary_if = NULL; struct net_device *hard_iface; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) || nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_priv->algo_ops->name) || nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, mesh_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, mesh_iface->name) || nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN, mesh_iface->dev_addr) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, (u8)atomic_read(&bat_priv->tt.vn))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, ntohs(bat_priv->bla.claim_dest.group))) goto nla_put_failure; #endif if (batadv_mcast_mesh_info_put(msg, bat_priv)) goto nla_put_failure; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { hard_iface = primary_if->net_dev; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hard_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, hard_iface->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, hard_iface->dev_addr)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED, !!atomic_read(&bat_priv->aggregated_ogms))) goto nla_put_failure; if (batadv_netlink_mesh_fill_ap_isolation(msg, bat_priv)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MARK, bat_priv->isolation_mark)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MASK, bat_priv->isolation_mark_mask)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_BONDING_ENABLED, !!atomic_read(&bat_priv->bonding))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u8(msg, BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, !!atomic_read(&bat_priv->bridge_loop_avoidance))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (nla_put_u8(msg, BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, !!atomic_read(&bat_priv->distributed_arp_table))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DAT */ if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED, !!atomic_read(&bat_priv->fragmentation))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_DOWN, atomic_read(&bat_priv->gw.bandwidth_down))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_UP, atomic_read(&bat_priv->gw.bandwidth_up))) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_GW_MODE, atomic_read(&bat_priv->gw.mode))) goto nla_put_failure; if (bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* GW selection class is not available if the routing algorithm * in use does not implement the GW API */ if (nla_put_u32(msg, BATADV_ATTR_GW_SEL_CLASS, atomic_read(&bat_priv->gw.sel_class))) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&bat_priv->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_DEBUG if (nla_put_u32(msg, BATADV_ATTR_LOG_LEVEL, atomic_read(&bat_priv->log_level))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, !atomic_read(&bat_priv->multicast_mode))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_MULTICAST_FANOUT, atomic_read(&bat_priv->multicast_fanout))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (nla_put_u8(msg, BATADV_ATTR_NETWORK_CODING_ENABLED, !!atomic_read(&bat_priv->network_coding))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_NC */ if (nla_put_u32(msg, BATADV_ATTR_ORIG_INTERVAL, atomic_read(&bat_priv->orig_interval))) goto nla_put_failure; batadv_hardif_put(primary_if); genlmsg_end(msg, hdr); return 0; nla_put_failure: batadv_hardif_put(primary_if); genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_mesh() - send meshif attributes to listener * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->mesh_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_mesh() - Get meshif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_mesh() - Set meshif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) { attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]; atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; batadv_netlink_set_mesh_ap_isolation(attr, bat_priv); } if (info->attrs[BATADV_ATTR_ISOLATION_MARK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MARK]; bat_priv->isolation_mark = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_ISOLATION_MASK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MASK]; bat_priv->isolation_mark_mask = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_BONDING_ENABLED]) { attr = info->attrs[BATADV_ATTR_BONDING_ENABLED]; atomic_set(&bat_priv->bonding, !!nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BLA if (info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]) { attr = info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]; atomic_set(&bat_priv->bridge_loop_avoidance, !!nla_get_u8(attr)); batadv_bla_status_update(bat_priv->mesh_iface); } #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]) { attr = info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]; atomic_set(&bat_priv->distributed_arp_table, !!nla_get_u8(attr)); batadv_dat_status_update(bat_priv->mesh_iface); } #endif /* CONFIG_BATMAN_ADV_DAT */ if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); rtnl_lock(); batadv_update_min_mtu(bat_priv->mesh_iface); rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]; atomic_set(&bat_priv->gw.bandwidth_down, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]; atomic_set(&bat_priv->gw.bandwidth_up, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_MODE]) { u8 gw_mode; attr = info->attrs[BATADV_ATTR_GW_MODE]; gw_mode = nla_get_u8(attr); if (gw_mode <= BATADV_GW_MODE_SERVER) { /* Invoking batadv_gw_reselect() is not enough to really * de-select the current GW. It will only instruct the * gateway client code to perform a re-election the next * time that this is needed. * * When gw client mode is being switched off the current * GW must be de-selected explicitly otherwise no GW_ADD * uevent is thrown on client mode re-activation. This * is operation is performed in * batadv_gw_check_client_stop(). */ batadv_gw_reselect(bat_priv); /* always call batadv_gw_check_client_stop() before * changing the gateway state */ batadv_gw_check_client_stop(bat_priv); atomic_set(&bat_priv->gw.mode, gw_mode); batadv_gw_tvlv_container_update(bat_priv); } } if (info->attrs[BATADV_ATTR_GW_SEL_CLASS] && bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* setting the GW selection class is allowed only if the routing * algorithm in use implements the GW API */ u32 sel_class_max = bat_priv->algo_ops->gw.sel_class_max; u32 sel_class; attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS]; sel_class = nla_get_u32(attr); if (sel_class >= 1 && sel_class <= sel_class_max) { atomic_set(&bat_priv->gw.sel_class, sel_class); batadv_gw_reselect(bat_priv); } } if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_DEBUG if (info->attrs[BATADV_ATTR_LOG_LEVEL]) { attr = info->attrs[BATADV_ATTR_LOG_LEVEL]; atomic_set(&bat_priv->log_level, nla_get_u32(attr) & BATADV_DBG_ALL); } #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]; atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_MULTICAST_FANOUT]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FANOUT]; atomic_set(&bat_priv->multicast_fanout, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]) { attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]; atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr)); batadv_nc_status_update(bat_priv->mesh_iface); } #endif /* CONFIG_BATMAN_ADV_NC */ if (info->attrs[BATADV_ATTR_ORIG_INTERVAL]) { u32 orig_interval; attr = info->attrs[BATADV_ATTR_ORIG_INTERVAL]; orig_interval = nla_get_u32(attr); orig_interval = min_t(u32, orig_interval, INT_MAX); orig_interval = max_t(u32, orig_interval, 2 * BATADV_JITTER); atomic_set(&bat_priv->orig_interval, orig_interval); } batadv_netlink_notify_mesh(bat_priv); return 0; } /** * batadv_netlink_tp_meter_put() - Fill information of started tp_meter session * @msg: netlink message to be sent back * @cookie: tp meter session cookie * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie) { if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) return -ENOBUFS; return 0; } /** * batadv_netlink_tpmeter_notify() - send tp_meter result via netlink to client * @bat_priv: the bat priv with all the mesh interface information * @dst: destination of tp_meter session * @result: reason for tp meter session stop * @test_time: total time of the tp_meter session * @total_bytes: bytes acked to the receiver * @cookie: cookie of tp_meter session * * Return: 0 on success, < 0 on error */ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie) { struct sk_buff *msg; void *hdr; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!hdr) { ret = -ENOBUFS; goto err_genlmsg; } if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_TPMETER_TEST_TIME, test_time)) goto nla_put_failure; if (nla_put_u64_64bit(msg, BATADV_ATTR_TPMETER_BYTES, total_bytes, BATADV_ATTR_PAD)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_TPMETER_RESULT, result)) goto nla_put_failure; if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, dst)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->mesh_iface), msg, 0, BATADV_NL_MCGRP_TPMETER, GFP_KERNEL); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); ret = -EMSGSIZE; err_genlmsg: nlmsg_free(msg); return ret; } /** * batadv_netlink_tp_meter_start() - Start a new tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg = NULL; u32 test_length; void *msg_head; u32 cookie; u8 *dst; int ret; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; } msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!msg_head) { ret = -ENOBUFS; goto out; } batadv_tp_start(bat_priv, dst, test_length, &cookie); ret = batadv_netlink_tp_meter_put(msg, cookie); out: if (ret) { if (msg) nlmsg_free(msg); return ret; } genlmsg_end(msg, msg_head); return genlmsg_reply(msg, info); } /** * batadv_netlink_tp_meter_cancel() - Cancel a running tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; u8 *dst; int ret = 0; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL); return ret; } /** * batadv_netlink_hardif_fill() - Fill message with hardif attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: hard interface which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * @cb: Control block containing additional options * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_hardif_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags, struct netlink_callback *cb) { struct net_device *net_dev = hard_iface->net_dev; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (cb) genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->mesh_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->mesh_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, net_dev->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, net_dev->dev_addr)) goto nla_put_failure; if (hard_iface->if_status == BATADV_IF_ACTIVE) { if (nla_put_flag(msg, BATADV_ATTR_ACTIVE)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&hard_iface->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (nla_put_u32(msg, BATADV_ATTR_ELP_INTERVAL, atomic_read(&hard_iface->bat_v.elp_interval))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT_OVERRIDE, atomic_read(&hard_iface->bat_v.throughput_override))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_hardif() - send hardif attributes to listener * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: hard interface which was modified * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->mesh_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_cmd_get_hardif() - Get hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_cmd_get_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, info->snd_portid, info->snd_seq, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_hardif() - Set hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&hard_iface->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); } if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { attr = info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]; atomic_set(&hard_iface->bat_v.throughput_override, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ batadv_netlink_notify_hardif(bat_priv, hard_iface); return 0; } /** * batadv_netlink_dump_hardif() - Dump all hard interface into a messages * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: error code, or length of reply message on success */ static int batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { struct net_device *mesh_iface; struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; int i = 0; mesh_iface = batadv_netlink_get_meshif(cb); if (IS_ERR(mesh_iface)) return PTR_ERR(mesh_iface); bat_priv = netdev_priv(mesh_iface); rtnl_lock(); cb->seq = batadv_hardif_generation << 1 | 1; list_for_each_entry(hard_iface, &batadv_hardif_list, list) { if (hard_iface->mesh_iface != mesh_iface) continue; if (i++ < skip) continue; if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb)) { i--; break; } } rtnl_unlock(); dev_put(mesh_iface); cb->args[0] = i; return msg->len; } /** * batadv_netlink_vlan_fill() - Fill message with vlan attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the mesh interface information * @vlan: vlan which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_vlan_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_meshif_vlan *vlan, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->mesh_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->mesh_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!atomic_read(&vlan->ap_isolation))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_vlan() - send vlan attributes to listener * @bat_priv: the bat priv with all the mesh interface information * @vlan: vlan which was modified * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, struct batadv_meshif_vlan *vlan) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_SET_VLAN, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->mesh_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_meshif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_meshif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); } batadv_netlink_notify_vlan(bat_priv, vlan); return 0; } /** * batadv_netlink_get_meshif_from_ifindex() - Get mesh-iface from ifindex * @net: the applicable net namespace * @ifindex: index of the mesh interface * * Return: Pointer to mesh interface (with increased refcnt) on success, error * pointer on error */ static struct net_device * batadv_netlink_get_meshif_from_ifindex(struct net *net, int ifindex) { struct net_device *mesh_iface; mesh_iface = dev_get_by_index(net, ifindex); if (!mesh_iface) return ERR_PTR(-ENODEV); if (!batadv_meshif_is_valid(mesh_iface)) goto err_put_meshif; return mesh_iface; err_put_meshif: dev_put(mesh_iface); return ERR_PTR(-EINVAL); } /** * batadv_netlink_get_meshif_from_info() - Get mesh-iface from genl attributes * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to mesh interface (with increased refcnt) on success, error * pointer on error */ static struct net_device * batadv_netlink_get_meshif_from_info(struct net *net, struct genl_info *info) { int ifindex; if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) return ERR_PTR(-EINVAL); ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); return batadv_netlink_get_meshif_from_ifindex(net, ifindex); } /** * batadv_netlink_get_meshif() - Retrieve mesh interface from netlink callback * @cb: callback structure containing arguments * * Return: Pointer to mesh interface (with increased refcnt) on success, error * pointer on error */ struct net_device *batadv_netlink_get_meshif(struct netlink_callback *cb) { int ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return ERR_PTR(-ENONET); return batadv_netlink_get_meshif_from_ifindex(sock_net(cb->skb->sk), ifindex); } /** * batadv_netlink_get_hardif_from_ifindex() - Get hard-iface from ifindex * @bat_priv: the bat priv with all the mesh interface information * @net: the applicable net namespace * @ifindex: index of the hard interface * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ static struct batadv_hard_iface * batadv_netlink_get_hardif_from_ifindex(struct batadv_priv *bat_priv, struct net *net, int ifindex) { struct batadv_hard_iface *hard_iface; struct net_device *hard_dev; hard_dev = dev_get_by_index(net, ifindex); if (!hard_dev) return ERR_PTR(-ENODEV); hard_iface = batadv_hardif_get_by_netdev(hard_dev); if (!hard_iface) goto err_put_harddev; if (hard_iface->mesh_iface != bat_priv->mesh_iface) goto err_put_hardif; /* hard_dev is referenced by hard_iface and not needed here */ dev_put(hard_dev); return hard_iface; err_put_hardif: batadv_hardif_put(hard_iface); err_put_harddev: dev_put(hard_dev); return ERR_PTR(-EINVAL); } /** * batadv_netlink_get_hardif_from_info() - Get hard-iface from genl attributes * @bat_priv: the bat priv with all the mesh interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ static struct batadv_hard_iface * batadv_netlink_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { int ifindex; if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) return ERR_PTR(-EINVAL); ifindex = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); return batadv_netlink_get_hardif_from_ifindex(bat_priv, net, ifindex); } /** * batadv_netlink_get_hardif() - Retrieve hard interface from netlink callback * @bat_priv: the bat priv with all the mesh interface information * @cb: callback structure containing arguments * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ struct batadv_hard_iface * batadv_netlink_get_hardif(struct batadv_priv *bat_priv, struct netlink_callback *cb) { int ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_HARD_IFINDEX); if (!ifindex) return ERR_PTR(-ENONET); return batadv_netlink_get_hardif_from_ifindex(bat_priv, sock_net(cb->skb->sk), ifindex); } /** * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes * @bat_priv: the bat priv with all the mesh interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to vlan on success (with increased refcnt), error pointer * on error */ static struct batadv_meshif_vlan * batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { struct batadv_meshif_vlan *vlan; u16 vid; if (!info->attrs[BATADV_ATTR_VLANID]) return ERR_PTR(-EINVAL); vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]); vlan = batadv_meshif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); if (!vlan) return ERR_PTR(-ENOENT); return vlan; } /** * batadv_pre_doit() - Prepare batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv = NULL; struct batadv_meshif_vlan *vlan; struct net_device *mesh_iface; u8 user_ptr1_flags; u8 mesh_dep_flags; int ret; user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1)) return -EINVAL; mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON((ops->internal_flags & mesh_dep_flags) && (~ops->internal_flags & BATADV_FLAG_NEED_MESH))) return -EINVAL; if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { mesh_iface = batadv_netlink_get_meshif_from_info(net, info); if (IS_ERR(mesh_iface)) return PTR_ERR(mesh_iface); bat_priv = netdev_priv(mesh_iface); info->user_ptr[0] = bat_priv; } if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { hard_iface = batadv_netlink_get_hardif_from_info(bat_priv, net, info); if (IS_ERR(hard_iface)) { ret = PTR_ERR(hard_iface); goto err_put_meshif; } info->user_ptr[1] = hard_iface; } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) { vlan = batadv_get_vlan_from_info(bat_priv, net, info); if (IS_ERR(vlan)) { ret = PTR_ERR(vlan); goto err_put_meshif; } info->user_ptr[1] = vlan; } return 0; err_put_meshif: if (bat_priv) dev_put(bat_priv->mesh_iface); return ret; } /** * batadv_post_doit() - End batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information */ static void batadv_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; struct batadv_meshif_vlan *vlan; struct batadv_priv *bat_priv; if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF && info->user_ptr[1]) { hard_iface = info->user_ptr[1]; batadv_hardif_put(hard_iface); } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) { vlan = info->user_ptr[1]; batadv_meshif_vlan_put(vlan); } if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) { bat_priv = info->user_ptr[0]; dev_put(bat_priv->mesh_iface); } } static const struct genl_small_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_start, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_cancel, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_algo_dump, }, { .cmd = BATADV_CMD_GET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .dumpit = batadv_netlink_dump_hardif, .doit = batadv_netlink_cmd_get_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_local_dump, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_global_dump, }, { .cmd = BATADV_CMD_GET_ORIGINATORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_orig_dump, }, { .cmd = BATADV_CMD_GET_NEIGHBORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_hardif_neigh_dump, }, { .cmd = BATADV_CMD_GET_GATEWAYS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_gw_dump, }, { .cmd = BATADV_CMD_GET_BLA_CLAIM, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_claim_dump, }, { .cmd = BATADV_CMD_GET_BLA_BACKBONE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_backbone_dump, }, { .cmd = BATADV_CMD_GET_DAT_CACHE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_dat_cache_dump, }, { .cmd = BATADV_CMD_GET_MCAST_FLAGS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_mcast_flags_dump, }, { .cmd = BATADV_CMD_SET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_SET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, { .cmd = BATADV_CMD_SET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, }; struct genl_family batadv_netlink_family __ro_after_init = { .hdrsize = 0, .name = BATADV_NL_NAME, .version = 1, .maxattr = BATADV_ATTR_MAX, .policy = batadv_netlink_policy, .netnsok = true, .pre_doit = batadv_pre_doit, .post_doit = batadv_post_doit, .module = THIS_MODULE, .small_ops = batadv_netlink_ops, .n_small_ops = ARRAY_SIZE(batadv_netlink_ops), .resv_start_op = BATADV_CMD_SET_VLAN + 1, .mcgrps = batadv_netlink_mcgrps, .n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps), }; /** * batadv_netlink_register() - register batadv genl netlink family */ void __init batadv_netlink_register(void) { int ret; ret = genl_register_family(&batadv_netlink_family); if (ret) pr_warn("unable to register netlink family\n"); } /** * batadv_netlink_unregister() - unregister batadv genl netlink family */ void batadv_netlink_unregister(void) { genl_unregister_family(&batadv_netlink_family); } |
| 17 16 1 1 5 5 5 16 1 15 15 2 19 2 2 2 2 2 2 2 1 19 3 1 3 3 3 3 3 1 1 1 3 3 3 3 14 14 14 14 2 2 2 14 31 9 1 18 11 7 5 8 8 9 1 8 8 8 8 7 14 2 11 1 2 46 2 1 2 41 1 3 39 39 2 2 2 5 2 3 2 1 2 6 12 2 2 15 3 86 1 39 2 16 5 9 1 51 4 22 24 2 18 1 17 2 2 29 1 1 1 1 1 10 10 4 13 14 14 12 1 2 2 4 2 1 3 1 2 16 3 4 1 3 1 4 1 6 4 5 2189 2186 455 6 4 7 1 1 5 5 146 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 | // SPDX-License-Identifier: GPL-2.0 /* XDP sockets * * AF_XDP sockets allows a channel between XDP programs and userspace * applications. * Copyright(c) 2018 Intel Corporation. * * Author(s): Björn Töpel <bjorn.topel@intel.com> * Magnus Karlsson <magnus.karlsson@intel.com> */ #define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__ #include <linux/if_xdp.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/vmalloc.h> #include <net/xdp_sock_drv.h> #include <net/busy_poll.h> #include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/xdp.h> #include "xsk_queue.h" #include "xdp_umem.h" #include "xsk.h" #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) return; pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; pool->cached_need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); pool->cached_need_wakeup |= XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX)) return; pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; pool->cached_need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); pool->cached_need_wakeup &= ~XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return pool->uses_need_wakeup; } EXPORT_SYMBOL(xsk_uses_need_wakeup); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->real_num_rx_queues) return dev->_rx[queue_id].pool; if (queue_id < dev->real_num_tx_queues) return dev->_tx[queue_id].pool; return NULL; } EXPORT_SYMBOL(xsk_get_pool_from_qid); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->num_rx_queues) dev->_rx[queue_id].pool = NULL; if (queue_id < dev->num_tx_queues) dev->_tx[queue_id].pool = NULL; } /* The buffer pool is stored both in the _rx struct and the _tx struct as we do * not know if the device has more tx queues than rx, or the opposite. * This might also change during run time. */ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id) { if (queue_id >= max_t(unsigned int, dev->real_num_rx_queues, dev->real_num_tx_queues)) return -EINVAL; if (queue_id < dev->real_num_rx_queues) dev->_rx[queue_id].pool = pool; if (queue_id < dev->real_num_tx_queues) dev->_tx[queue_id].pool = pool; return 0; } static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len, u32 flags) { u64 addr; int err; addr = xp_get_handle(xskb, xskb->pool); err = xskq_prod_reserve_desc(xs->rx, addr, len, flags); if (err) { xs->rx_queue_full++; return err; } xp_release(xskb); return 0; } static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); u32 frags = xdp_buff_has_frags(xdp); struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; int err; if (frags) contd = XDP_PKT_CONTD; err = __xsk_rcv_zc(xs, xskb, len, contd); if (err) goto err; if (likely(!frags)) return 0; xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; err = __xsk_rcv_zc(xs, pos, len, contd); if (err) goto err; list_del(&pos->list_node); } return 0; err: xsk_buff_free(xdp); return err; } static void *xsk_copy_xdp_start(struct xdp_buff *from) { if (unlikely(xdp_data_meta_unsupported(from))) return from->data; else return from->data_meta; } static u32 xsk_copy_xdp(void *to, void **from, u32 to_len, u32 *from_len, skb_frag_t **frag, u32 rem) { u32 copied = 0; while (1) { u32 copy_len = min_t(u32, *from_len, to_len); memcpy(to, *from, copy_len); copied += copy_len; if (rem == copied) return copied; if (*from_len == copy_len) { *from = skb_frag_address(*frag); *from_len = skb_frag_size((*frag)++); } else { *from += copy_len; *from_len -= copy_len; } if (to_len == copy_len) return copied; to_len -= copy_len; to += copy_len; } } static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool); void *copy_from = xsk_copy_xdp_start(xdp), *copy_to; u32 from_len, meta_len, rem, num_desc; struct xdp_buff_xsk *xskb; struct xdp_buff *xsk_xdp; skb_frag_t *frag; from_len = xdp->data_end - copy_from; meta_len = xdp->data - copy_from; rem = len + meta_len; if (len <= frame_size && !xdp_buff_has_frags(xdp)) { int err; xsk_xdp = xsk_buff_alloc(xs->pool); if (!xsk_xdp) { xs->rx_dropped++; return -ENOMEM; } memcpy(xsk_xdp->data - meta_len, copy_from, rem); xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); err = __xsk_rcv_zc(xs, xskb, len, 0); if (err) { xsk_buff_free(xsk_xdp); return err; } return 0; } num_desc = (len - 1) / frame_size + 1; if (!xsk_buff_can_alloc(xs->pool, num_desc)) { xs->rx_dropped++; return -ENOMEM; } if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { xs->rx_queue_full++; return -ENOBUFS; } if (xdp_buff_has_frags(xdp)) { struct skb_shared_info *sinfo; sinfo = xdp_get_shared_info_from_buff(xdp); frag = &sinfo->frags[0]; } do { u32 to_len = frame_size + meta_len; u32 copied; xsk_xdp = xsk_buff_alloc(xs->pool); copy_to = xsk_xdp->data - meta_len; copied = xsk_copy_xdp(copy_to, ©_from, to_len, &from_len, &frag, rem); rem -= copied; xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); __xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0); meta_len = 0; } while (rem); return 0; } static bool xsk_tx_writeable(struct xdp_sock *xs) { if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2) return false; return true; } static bool xsk_is_bound(struct xdp_sock *xs) { if (READ_ONCE(xs->state) == XSK_BOUND) { /* Matches smp_wmb() in bind(). */ smp_rmb(); return true; } return false; } static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { if (!xsk_is_bound(xs)) return -ENXIO; if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) return -EINVAL; if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) { xs->rx_dropped++; return -ENOSPC; } return 0; } static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); __xskq_cons_release(xs->pool->fq); sock_def_readable(&xs->sk); } int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len = xdp_get_buff_len(xdp); int err; err = xsk_rcv_check(xs, xdp, len); if (!err) { spin_lock_bh(&xs->pool->rx_lock); err = __xsk_rcv(xs, xdp, len); xsk_flush(xs); spin_unlock_bh(&xs->pool->rx_lock); } return err; } static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len = xdp_get_buff_len(xdp); int err; err = xsk_rcv_check(xs, xdp, len); if (err) return err; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) { len = xdp->data_end - xdp->data; return xsk_rcv_zc(xs, xdp, len); } err = __xsk_rcv(xs, xdp, len); if (!err) xdp_return_buff(xdp); return err; } int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { int err; err = xsk_rcv(xs, xdp); if (err) return err; if (!xs->flush_node.prev) { struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list(); list_add(&xs->flush_node, flush_list); } return 0; } void __xsk_map_flush(struct list_head *flush_list) { struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { xsk_flush(xs); __list_del_clearprev(&xs->flush_node); } } void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { xskq_prod_submit_n(pool->cq, nb_entries); } EXPORT_SYMBOL(xsk_tx_completed); void xsk_tx_release(struct xsk_buff_pool *pool) { struct xdp_sock *xs; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); if (xsk_tx_writeable(xs)) xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } EXPORT_SYMBOL(xsk_tx_release); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { bool budget_exhausted = false; struct xdp_sock *xs; rcu_read_lock(); again: list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { if (xs->tx_budget_spent >= MAX_PER_SOCKET_BUDGET) { budget_exhausted = true; continue; } if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { if (xskq_has_descs(xs->tx)) xskq_cons_release(xs->tx); continue; } xs->tx_budget_spent++; /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ if (xskq_prod_reserve_addr(pool->cq, desc->addr)) goto out; xskq_cons_release(xs->tx); rcu_read_unlock(); return true; } if (budget_exhausted) { list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) xs->tx_budget_spent = 0; budget_exhausted = false; goto again; } out: rcu_read_unlock(); return false; } EXPORT_SYMBOL(xsk_tx_peek_desc); static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entries) { struct xdp_desc *descs = pool->tx_descs; u32 nb_pkts = 0; while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts])) nb_pkts++; xsk_tx_release(pool); return nb_pkts; } u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 nb_pkts) { struct xdp_sock *xs; rcu_read_lock(); if (!list_is_singular(&pool->xsk_tx_list)) { /* Fallback to the non-batched version */ rcu_read_unlock(); return xsk_tx_peek_release_fallback(pool, nb_pkts); } xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list); if (!xs) { nb_pkts = 0; goto out; } nb_pkts = xskq_cons_nb_entries(xs->tx, nb_pkts); /* This is the backpressure mechanism for the Tx path. Try to * reserve space in the completion queue for all packets, but * if there are fewer slots available, just process that many * packets. This avoids having to implement any buffering in * the Tx path. */ nb_pkts = xskq_prod_nb_free(pool->cq, nb_pkts); if (!nb_pkts) goto out; nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, nb_pkts); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; } __xskq_cons_release(xs->tx); xskq_prod_write_addr_batch(pool->cq, pool->tx_descs, nb_pkts); xs->sk.sk_write_space(&xs->sk); out: rcu_read_unlock(); return nb_pkts; } EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch); static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr) { unsigned long flags; int ret; spin_lock_irqsave(&pool->cq_lock, flags); ret = xskq_prod_reserve_addr(pool->cq, addr); spin_unlock_irqrestore(&pool->cq_lock, flags); return ret; } static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n) { unsigned long flags; spin_lock_irqsave(&pool->cq_lock, flags); xskq_prod_submit_n(pool->cq, n); spin_unlock_irqrestore(&pool->cq_lock, flags); } static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) { unsigned long flags; spin_lock_irqsave(&pool->cq_lock, flags); xskq_prod_cancel_n(pool->cq, n); spin_unlock_irqrestore(&pool->cq_lock, flags); } static u32 xsk_get_num_desc(struct sk_buff *skb) { return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; } static void xsk_destruct_skb(struct sk_buff *skb) { struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta; if (compl->tx_timestamp) { /* sw completion timestamp, not a real one */ *compl->tx_timestamp = ktime_get_tai_fast_ns(); } xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb)); sock_wfree(skb); } static void xsk_set_destructor_arg(struct sk_buff *skb) { long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; skb_shinfo(skb)->destructor_arg = (void *)num; } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); skb->destructor = sock_wfree; xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb)); /* Free skb without triggering the perf drop trace */ consume_skb(skb); xs->skb = NULL; } static void xsk_drop_skb(struct sk_buff *skb) { xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb); xsk_consume_skb(skb); } static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, struct xdp_desc *desc) { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; int err, i; u64 addr; if (!skb) { hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom)); skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err); if (unlikely(!skb)) return ERR_PTR(err); skb_reserve(skb, hr); } addr = desc->addr; len = desc->len; ts = pool->unaligned ? len : pool->chunk_size; buffer = xsk_buff_raw_get_data(pool, addr); offset = offset_in_page(buffer); addr = buffer - pool->addrs; for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) { if (unlikely(i >= MAX_SKB_FRAGS)) return ERR_PTR(-EOVERFLOW); page = pool->umem->pgs[addr >> PAGE_SHIFT]; get_page(page); copy = min_t(u32, PAGE_SIZE - offset, len - copied); skb_fill_page_desc(skb, i, page, offset, copy); copied += copy; addr += copy; offset = 0; } skb->len += len; skb->data_len += len; skb->truesize += ts; refcount_add(ts, &xs->sk.sk_wmem_alloc); return skb; } static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, struct xdp_desc *desc) { struct xsk_tx_metadata *meta = NULL; struct net_device *dev = xs->dev; struct sk_buff *skb = xs->skb; bool first_frag = false; int err; if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { skb = xsk_build_skb_zerocopy(xs, desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); goto free_err; } } else { u32 hr, tr, len; void *buffer; buffer = xsk_buff_raw_get_data(xs->pool, desc->addr); len = desc->len; if (!skb) { first_frag = true; hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)); tr = dev->needed_tailroom; skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err); if (unlikely(!skb)) goto free_err; skb_reserve(skb, hr); skb_put(skb, len); err = skb_store_bits(skb, 0, buffer, len); if (unlikely(err)) goto free_err; } else { int nr_frags = skb_shinfo(skb)->nr_frags; struct page *page; u8 *vaddr; if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { err = -EOVERFLOW; goto free_err; } page = alloc_page(xs->sk.sk_allocation); if (unlikely(!page)) { err = -EAGAIN; goto free_err; } vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); } if (first_frag && desc->options & XDP_TX_METADATA) { if (unlikely(xs->pool->tx_metadata_len == 0)) { err = -EINVAL; goto free_err; } meta = buffer - xs->pool->tx_metadata_len; if (unlikely(!xsk_buff_valid_tx_metadata(meta))) { err = -EINVAL; goto free_err; } if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { if (unlikely(meta->request.csum_start + meta->request.csum_offset + sizeof(__sum16) > len)) { err = -EINVAL; goto free_err; } skb->csum_start = hr + meta->request.csum_start; skb->csum_offset = meta->request.csum_offset; skb->ip_summed = CHECKSUM_PARTIAL; if (unlikely(xs->pool->tx_sw_csum)) { err = skb_checksum_help(skb); if (err) goto free_err; } } if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) skb->skb_mstamp_ns = meta->request.launch_time; } } skb->dev = dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); xsk_set_destructor_arg(skb); return skb; free_err: if (first_frag && skb) kfree_skb(skb); if (err == -EOVERFLOW) { /* Drop the packet */ xsk_set_destructor_arg(xs->skb); xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } else { /* Let application retry */ xsk_cq_cancel_locked(xs->pool, 1); } return ERR_PTR(err); } static int __xsk_generic_xmit(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); u32 max_batch = TX_BATCH_SIZE; bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; int err = 0; mutex_lock(&xs->mutex); /* Since we dropped the RCU read lock, the socket state might have changed. */ if (unlikely(!xsk_is_bound(xs))) { err = -ENXIO; goto out; } if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { if (max_batch-- == 0) { err = -EAGAIN; goto out; } /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr); if (err) { err = -EAGAIN; goto out; } skb = xsk_build_skb(xs, &desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); if (err != -EOVERFLOW) goto out; err = 0; continue; } xskq_cons_release(xs->tx); if (xp_mb_desc(&desc)) { xs->skb = skb; continue; } err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ xskq_cons_cancel_n(xs->tx, xsk_get_num_desc(skb)); xsk_consume_skb(skb); err = -EAGAIN; goto out; } /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ err = -EBUSY; xs->skb = NULL; goto out; } sent_frame = true; xs->skb = NULL; } if (xskq_has_descs(xs->tx)) { if (xs->skb) xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } out: if (sent_frame) if (xsk_tx_writeable(xs)) sk->sk_write_space(sk); mutex_unlock(&xs->mutex); return err; } static int xsk_generic_xmit(struct sock *sk) { int ret; /* Drop the RCU lock since the SKB path might sleep. */ rcu_read_unlock(); ret = __xsk_generic_xmit(sk); /* Reaquire RCU lock before going into common code. */ rcu_read_lock(); return ret; } static bool xsk_no_wakeup(struct sock *sk) { #ifdef CONFIG_NET_RX_BUSY_POLL /* Prefer busy-polling, skip the wakeup. */ return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) && napi_id_valid(READ_ONCE(sk->sk_napi_id)); #else return false; #endif } static int xsk_check_common(struct xdp_sock *xs) { if (unlikely(!xsk_is_bound(xs))) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; return 0; } static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; int err; err = xsk_check_common(xs); if (err) return err; if (unlikely(need_wait)) return -EOPNOTSUPP; if (unlikely(!xs->tx)) return -ENOBUFS; if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; if (pool->cached_need_wakeup & XDP_WAKEUP_TX) { if (xs->zc) return xsk_wakeup(xs, XDP_WAKEUP_TX); return xsk_generic_xmit(sk); } return 0; } static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret; rcu_read_lock(); ret = __xsk_sendmsg(sock, m, total_len); rcu_read_unlock(); return ret; } static int __xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { bool need_wait = !(flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int err; err = xsk_check_common(xs); if (err) return err; if (unlikely(!xs->rx)) return -ENOBUFS; if (unlikely(need_wait)) return -EOPNOTSUPP; if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ if (xsk_no_wakeup(sk)) return 0; if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc) return xsk_wakeup(xs, XDP_WAKEUP_RX); return 0; } static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { int ret; rcu_read_lock(); ret = __xsk_recvmsg(sock, m, len, flags); rcu_read_unlock(); return ret; } static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { __poll_t mask = 0; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; sock_poll_wait(file, sock, wait); rcu_read_lock(); if (xsk_check_common(xs)) goto out; pool = xs->pool; if (pool->cached_need_wakeup) { if (xs->zc) xsk_wakeup(xs, pool->cached_need_wakeup); else if (xs->tx) /* Poll needs to drive Tx also in copy mode */ xsk_generic_xmit(sk); } if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; out: rcu_read_unlock(); return mask; } static int xsk_init_queue(u32 entries, struct xsk_queue **queue, bool umem_queue) { struct xsk_queue *q; if (entries == 0 || *queue || !is_power_of_2(entries)) return -EINVAL; q = xskq_create(entries, umem_queue); if (!q) return -ENOMEM; /* Make sure queue is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(*queue, q); return 0; } static void xsk_unbind_dev(struct xdp_sock *xs) { struct net_device *dev = xs->dev; if (xs->state != XSK_BOUND) return; WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ xp_del_xsk(xs->pool, xs); synchronize_net(); dev_put(dev); } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; *map_entry = NULL; spin_lock_bh(&xs->map_list_lock); node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node, node); if (node) { bpf_map_inc(&node->map->map); map = node->map; *map_entry = node->map_entry; } spin_unlock_bh(&xs->map_list_lock); return map; } static void xsk_delete_from_maps(struct xdp_sock *xs) { /* This function removes the current XDP socket from all the * maps it resides in. We need to take extra care here, due to * the two locks involved. Each map has a lock synchronizing * updates to the entries, and each socket has a lock that * synchronizes access to the list of maps (map_list). For * deadlock avoidance the locks need to be taken in the order * "map lock"->"socket map list lock". We start off by * accessing the socket map list, and take a reference to the * map to guarantee existence between the * xsk_get_map_list_entry() and xsk_map_try_sock_delete() * calls. Then we ask the map to remove the socket, which * tries to remove the socket from the map. Note that there * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { xsk_map_try_sock_delete(map, xs, map_entry); bpf_map_put(&map->map); } } static int xsk_release(struct socket *sock) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net *net; if (!sk) return 0; net = sock_net(sk); if (xs->skb) xsk_drop_skb(xs->skb); mutex_lock(&net->xdp.lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->xdp.lock); sock_prot_inuse_add(net, sk->sk_prot, -1); xsk_delete_from_maps(xs); mutex_lock(&xs->mutex); xsk_unbind_dev(xs); mutex_unlock(&xs->mutex); xskq_destroy(xs->rx); xskq_destroy(xs->tx); xskq_destroy(xs->fq_tmp); xskq_destroy(xs->cq_tmp); sock_orphan(sk); sock->sk = NULL; sock_put(sk); return 0; } static struct socket *xsk_lookup_xsk_from_fd(int fd) { struct socket *sock; int err; sock = sockfd_lookup(fd, &err); if (!sock) return ERR_PTR(-ENOTSOCK); if (sock->sk->sk_family != PF_XDP) { sockfd_put(sock); return ERR_PTR(-ENOPROTOOPT); } return sock; } static bool xsk_validate_queues(struct xdp_sock *xs) { return xs->fq_tmp && xs->cq_tmp; } static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; int bound_dev_if; u32 flags, qid; int err = 0; if (addr_len < sizeof(struct sockaddr_xdp)) return -EINVAL; if (sxdp->sxdp_family != AF_XDP) return -EINVAL; flags = sxdp->sxdp_flags; if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY | XDP_USE_NEED_WAKEUP | XDP_USE_SG)) return -EINVAL; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && bound_dev_if != sxdp->sxdp_ifindex) return -EINVAL; rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { err = -EBUSY; goto out_release; } dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex); if (!dev) { err = -ENODEV; goto out_release; } netdev_lock_ops(dev); if (!xs->rx && !xs->tx) { err = -EINVAL; goto out_unlock; } qid = sxdp->sxdp_queue_id; if (flags & XDP_SHARED_UMEM) { struct xdp_sock *umem_xs; struct socket *sock; if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) || (flags & XDP_USE_NEED_WAKEUP) || (flags & XDP_USE_SG)) { /* Cannot specify flags for shared sockets. */ err = -EINVAL; goto out_unlock; } if (xs->umem) { /* We have already our own. */ err = -EINVAL; goto out_unlock; } sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); if (IS_ERR(sock)) { err = PTR_ERR(sock); goto out_unlock; } umem_xs = xdp_sk(sock->sk); if (!xsk_is_bound(umem_xs)) { err = -EBADF; sockfd_put(sock); goto out_unlock; } if (umem_xs->queue_id != qid || umem_xs->dev != dev) { /* Share the umem with another socket on another qid * and/or device. */ xs->pool = xp_create_and_assign_umem(xs, umem_xs->umem); if (!xs->pool) { err = -ENOMEM; sockfd_put(sock); goto out_unlock; } err = xp_assign_dev_shared(xs->pool, umem_xs, dev, qid); if (err) { xp_destroy(xs->pool); xs->pool = NULL; sockfd_put(sock); goto out_unlock; } } else { /* Share the buffer pool with the other socket. */ if (xs->fq_tmp || xs->cq_tmp) { /* Do not allow setting your own fq or cq. */ err = -EINVAL; sockfd_put(sock); goto out_unlock; } xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; /* If underlying shared umem was created without Tx * ring, allocate Tx descs array that Tx batching API * utilizes */ if (xs->tx && !xs->pool->tx_descs) { err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); xs->pool = NULL; sockfd_put(sock); goto out_unlock; } } } xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); } else if (!xs->umem || !xsk_validate_queues(xs)) { err = -EINVAL; goto out_unlock; } else { /* This xsk has its own umem. */ xs->pool = xp_create_and_assign_umem(xs, xs->umem); if (!xs->pool) { err = -ENOMEM; goto out_unlock; } err = xp_assign_dev(xs->pool, dev, qid, flags); if (err) { xp_destroy(xs->pool); xs->pool = NULL; goto out_unlock; } } /* FQ and CQ are now owned by the buffer pool and cleaned up with it. */ xs->fq_tmp = NULL; xs->cq_tmp = NULL; xs->dev = dev; xs->zc = xs->umem->zc; xs->sg = !!(xs->umem->flags & XDP_UMEM_SG_FLAG); xs->queue_id = qid; xp_add_xsk(xs->pool, xs); if (qid < dev->real_num_rx_queues) { struct netdev_rx_queue *rxq; rxq = __netif_get_rx_queue(dev, qid); if (rxq->napi) __sk_mark_napi_id_once(sk, rxq->napi->napi_id); } out_unlock: if (err) { dev_put(dev); } else { /* Matches smp_rmb() in bind() for shared umem * sockets, and xsk_is_bound(). */ smp_wmb(); WRITE_ONCE(xs->state, XSK_BOUND); } netdev_unlock_ops(dev); out_release: mutex_unlock(&xs->mutex); rtnl_unlock(); return err; } struct xdp_umem_reg_v1 { __u64 addr; /* Start of packet data area */ __u64 len; /* Length of packet data area */ __u32 chunk_size; __u32 headroom; }; static int xsk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int err; if (level != SOL_XDP) return -ENOPROTOOPT; switch (optname) { case XDP_RX_RING: case XDP_TX_RING: { struct xsk_queue **q; int entries; if (optlen < sizeof(entries)) return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { mutex_unlock(&xs->mutex); return -EBUSY; } q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; err = xsk_init_queue(entries, q, false); if (!err && optname == XDP_TX_RING) /* Tx needs to be explicitly woken up the first time */ xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; mutex_unlock(&xs->mutex); return err; } case XDP_UMEM_REG: { size_t mr_size = sizeof(struct xdp_umem_reg); struct xdp_umem_reg mr = {}; struct xdp_umem *umem; if (optlen < sizeof(struct xdp_umem_reg_v1)) return -EINVAL; else if (optlen < sizeof(mr)) mr_size = sizeof(struct xdp_umem_reg_v1); BUILD_BUG_ON(sizeof(struct xdp_umem_reg_v1) >= sizeof(struct xdp_umem_reg)); /* Make sure the last field of the struct doesn't have * uninitialized padding. All padding has to be explicit * and has to be set to zero by the userspace to make * struct xdp_umem_reg extensible in the future. */ BUILD_BUG_ON(offsetof(struct xdp_umem_reg, tx_metadata_len) + sizeof_field(struct xdp_umem_reg, tx_metadata_len) != sizeof(struct xdp_umem_reg)); if (copy_from_sockptr(&mr, optval, mr_size)) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY || xs->umem) { mutex_unlock(&xs->mutex); return -EBUSY; } umem = xdp_umem_create(&mr); if (IS_ERR(umem)) { mutex_unlock(&xs->mutex); return PTR_ERR(umem); } /* Make sure umem is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(xs->umem, umem); mutex_unlock(&xs->mutex); return 0; } case XDP_UMEM_FILL_RING: case XDP_UMEM_COMPLETION_RING: { struct xsk_queue **q; int entries; if (optlen < sizeof(entries)) return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { mutex_unlock(&xs->mutex); return -EBUSY; } q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : &xs->cq_tmp; err = xsk_init_queue(entries, q, true); mutex_unlock(&xs->mutex); return err; } default: break; } return -ENOPROTOOPT; } static void xsk_enter_rxtx_offsets(struct xdp_ring_offset_v1 *ring) { ring->producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); ring->consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); ring->desc = offsetof(struct xdp_rxtx_ring, desc); } static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring) { ring->producer = offsetof(struct xdp_umem_ring, ptrs.producer); ring->consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); ring->desc = offsetof(struct xdp_umem_ring, desc); } struct xdp_statistics_v1 { __u64 rx_dropped; __u64 rx_invalid_descs; __u64 tx_invalid_descs; }; static int xsk_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int len; if (level != SOL_XDP) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case XDP_STATISTICS: { struct xdp_statistics stats = {}; bool extra_stats = true; size_t stats_size; if (len < sizeof(struct xdp_statistics_v1)) { return -EINVAL; } else if (len < sizeof(stats)) { extra_stats = false; stats_size = sizeof(struct xdp_statistics_v1); } else { stats_size = sizeof(stats); } mutex_lock(&xs->mutex); stats.rx_dropped = xs->rx_dropped; if (extra_stats) { stats.rx_ring_full = xs->rx_queue_full; stats.rx_fill_ring_empty_descs = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx); } else { stats.rx_dropped += xs->rx_queue_full; } stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx); stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx); mutex_unlock(&xs->mutex); if (copy_to_user(optval, &stats, stats_size)) return -EFAULT; if (put_user(stats_size, optlen)) return -EFAULT; return 0; } case XDP_MMAP_OFFSETS: { struct xdp_mmap_offsets off; struct xdp_mmap_offsets_v1 off_v1; bool flags_supported = true; void *to_copy; if (len < sizeof(off_v1)) return -EINVAL; else if (len < sizeof(off)) flags_supported = false; if (flags_supported) { /* xdp_ring_offset is identical to xdp_ring_offset_v1 * except for the flags field added to the end. */ xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) &off.rx); xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) &off.tx); xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) &off.fr); xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) &off.cr); off.rx.flags = offsetof(struct xdp_rxtx_ring, ptrs.flags); off.tx.flags = offsetof(struct xdp_rxtx_ring, ptrs.flags); off.fr.flags = offsetof(struct xdp_umem_ring, ptrs.flags); off.cr.flags = offsetof(struct xdp_umem_ring, ptrs.flags); len = sizeof(off); to_copy = &off; } else { xsk_enter_rxtx_offsets(&off_v1.rx); xsk_enter_rxtx_offsets(&off_v1.tx); xsk_enter_umem_offsets(&off_v1.fr); xsk_enter_umem_offsets(&off_v1.cr); len = sizeof(off_v1); to_copy = &off_v1; } if (copy_to_user(optval, to_copy, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } case XDP_OPTIONS: { struct xdp_options opts = {}; if (len < sizeof(opts)) return -EINVAL; mutex_lock(&xs->mutex); if (xs->zc) opts.flags |= XDP_OPTIONS_ZEROCOPY; mutex_unlock(&xs->mutex); len = sizeof(opts); if (copy_to_user(optval, &opts, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } default: break; } return -EOPNOTSUPP; } static int xsk_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { loff_t offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); int state = READ_ONCE(xs->state); struct xsk_queue *q = NULL; if (state != XSK_READY && state != XSK_BOUND) return -EBUSY; if (offset == XDP_PGOFF_RX_RING) { q = READ_ONCE(xs->rx); } else if (offset == XDP_PGOFF_TX_RING) { q = READ_ONCE(xs->tx); } else { /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) q = state == XSK_READY ? READ_ONCE(xs->fq_tmp) : READ_ONCE(xs->pool->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) q = state == XSK_READY ? READ_ONCE(xs->cq_tmp) : READ_ONCE(xs->pool->cq); } if (!q) return -EINVAL; /* Matches the smp_wmb() in xsk_init_queue */ smp_rmb(); if (size > q->ring_vmalloc_size) return -EINVAL; return remap_vmalloc_range(vma, q->ring, 0); } static int xsk_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct sock *sk; switch (msg) { case NETDEV_UNREGISTER: mutex_lock(&net->xdp.lock); sk_for_each(sk, &net->xdp.list) { struct xdp_sock *xs = xdp_sk(sk); mutex_lock(&xs->mutex); if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); xsk_unbind_dev(xs); /* Clear device references. */ xp_clear_dev(xs->pool); } mutex_unlock(&xs->mutex); } mutex_unlock(&net->xdp.lock); break; } return NOTIFY_DONE; } static struct proto xsk_proto = { .name = "XDP", .owner = THIS_MODULE, .obj_size = sizeof(struct xdp_sock), }; static const struct proto_ops xsk_proto_ops = { .family = PF_XDP, .owner = THIS_MODULE, .release = xsk_release, .bind = xsk_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = xsk_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = xsk_setsockopt, .getsockopt = xsk_getsockopt, .sendmsg = xsk_sendmsg, .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, }; static void xsk_destruct(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); if (!sock_flag(sk, SOCK_DEAD)) return; if (!xp_put_pool(xs->pool)) xdp_put_umem(xs->umem, !xs->pool); } static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { struct xdp_sock *xs; struct sock *sk; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (protocol) return -EPROTONOSUPPORT; sock->state = SS_UNCONNECTED; sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern); if (!sk) return -ENOBUFS; sock->ops = &xsk_proto_ops; sock_init_data(sock, sk); sk->sk_family = PF_XDP; sk->sk_destruct = xsk_destruct; sock_set_flag(sk, SOCK_RCU_FREE); xs = xdp_sk(sk); xs->state = XSK_READY; mutex_init(&xs->mutex); INIT_LIST_HEAD(&xs->map_list); spin_lock_init(&xs->map_list_lock); mutex_lock(&net->xdp.lock); sk_add_node_rcu(sk, &net->xdp.list); mutex_unlock(&net->xdp.lock); sock_prot_inuse_add(net, &xsk_proto, 1); return 0; } static const struct net_proto_family xsk_family_ops = { .family = PF_XDP, .create = xsk_create, .owner = THIS_MODULE, }; static struct notifier_block xsk_netdev_notifier = { .notifier_call = xsk_notifier, }; static int __net_init xsk_net_init(struct net *net) { mutex_init(&net->xdp.lock); INIT_HLIST_HEAD(&net->xdp.list); return 0; } static void __net_exit xsk_net_exit(struct net *net) { WARN_ON_ONCE(!hlist_empty(&net->xdp.list)); } static struct pernet_operations xsk_net_ops = { .init = xsk_net_init, .exit = xsk_net_exit, }; static int __init xsk_init(void) { int err; err = proto_register(&xsk_proto, 0 /* no slab */); if (err) goto out; err = sock_register(&xsk_family_ops); if (err) goto out_proto; err = register_pernet_subsys(&xsk_net_ops); if (err) goto out_sk; err = register_netdevice_notifier(&xsk_netdev_notifier); if (err) goto out_pernet; return 0; out_pernet: unregister_pernet_subsys(&xsk_net_ops); out_sk: sock_unregister(PF_XDP); out_proto: proto_unregister(&xsk_proto); out: return err; } fs_initcall(xsk_init); |
| 1541 1539 1542 1334 1540 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/symlink.c - kernfs symlink implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/gfp.h> #include <linux/namei.h> #include "kernfs-internal.h" /** * kernfs_create_link - create a symlink * @parent: directory to create the symlink in * @name: name of the symlink * @target: target node for the symlink to point to * * Return: the created node on success, ERR_PTR() value on error. * Ownership of the link matches ownership of the target. */ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { struct kernfs_node *kn; int error; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; if (target->iattr) { uid = target->iattr->ia_uid; gid = target->iattr->ia_gid; } kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK); if (!kn) return ERR_PTR(-ENOMEM); if (kernfs_ns_enabled(parent)) kn->ns = target->ns; kn->symlink.target_kn = target; kernfs_get(target); /* ref owned by symlink */ error = kernfs_add_one(kn); if (!error) return kn; kernfs_put(kn); return ERR_PTR(error); } static int kernfs_get_target_path(struct kernfs_node *parent, struct kernfs_node *target, char *path) { struct kernfs_node *base, *kn; char *s = path; int len = 0; /* go up to the root, stop at the base */ base = parent; while (kernfs_parent(base)) { kn = kernfs_parent(target); while (kernfs_parent(kn) && base != kn) kn = kernfs_parent(kn); if (base == kn) break; if ((s - path) + 3 >= PATH_MAX) return -ENAMETOOLONG; strcpy(s, "../"); s += 3; base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; while (kernfs_parent(kn) && kn != base) { len += strlen(kernfs_rcu_name(kn)) + 1; kn = kernfs_parent(kn); } /* check limits */ if (len < 2) return -EINVAL; len--; if ((s - path) + len >= PATH_MAX) return -ENAMETOOLONG; /* reverse fillup of target string from target to base */ kn = target; while (kernfs_parent(kn) && kn != base) { const char *name = kernfs_rcu_name(kn); int slen = strlen(name); len -= slen; memcpy(s + len, name, slen); if (len) s[--len] = '/'; kn = kernfs_parent(kn); } return 0; } static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); return error; } static const char *kernfs_iop_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { char *body; int error; if (!dentry) return ERR_PTR(-ECHILD); body = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!body) return ERR_PTR(-ENOMEM); error = kernfs_getlink(inode, body); if (unlikely(error < 0)) { kfree(body); return ERR_PTR(error); } set_delayed_call(done, kfree_link, body); return body; } const struct inode_operations kernfs_symlink_iops = { .listxattr = kernfs_iop_listxattr, .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, }; |
| 40 1755 18 28 20 1 66 1226 221 189 116 9 14 1 182 958 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ #include <linux/bitfield.h> #include <linux/bug.h> #include <linux/const.h> #include <linux/limits.h> #define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) #define FORTIFY_REASON_DIR(r) FIELD_GET(BIT(0), r) #define FORTIFY_REASON_FUNC(r) FIELD_GET(GENMASK(7, 1), r) #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) /* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif #ifndef fortify_warn_once # define fortify_warn_once(x...) WARN_ONCE(x) #endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 #define EACH_FORTIFY_FUNC(macro) \ macro(strncpy), \ macro(strnlen), \ macro(strlen), \ macro(strscpy), \ macro(strlcat), \ macro(strcat), \ macro(strncat), \ macro(memset), \ macro(memcpy), \ macro(memmove), \ macro(memscan), \ macro(memcmp), \ macro(memchr), \ macro(memchr_inv), \ macro(kmemdup), \ macro(strcpy), \ macro(UNKNOWN), #define MAKE_FORTIFY_FUNC(func) FORTIFY_FUNC_##func enum fortify_func { EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC) }; void __fortify_report(const u8 reason, const size_t avail, const size_t size); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) __cold __noreturn; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ char *__p = (char *)(p); \ size_t __ret = SIZE_MAX; \ const size_t __p_size = __member_size(p); \ if (__p_size != SIZE_MAX && \ __builtin_constant_p(*__p)) { \ size_t __p_len = __p_size - 1; \ if (__builtin_constant_p(__p[__p_len]) && \ __p[__p_len] == '\0') \ __ret = __builtin_strlen(__p); \ } \ __ret; \ }) #if defined(__SANITIZE_ADDRESS__) #if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); #elif defined(CONFIG_KASAN_GENERIC) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); #else /* CONFIG_KASAN_SW_TAGS */ extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); #endif extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #if defined(__SANITIZE_MEMORY__) /* * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the * corresponding __msan_XXX functions. */ #include <linux/kmsan_string.h> #define __underlying_memcpy __msan_memcpy #define __underlying_memmove __msan_memmove #define __underlying_memset __msan_memset #else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #endif #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif /** * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking * * @dst: Destination memory address to write to * @src: Source memory address to read from * @bytes: How many bytes to write to @dst from @src * @justification: Free-form text or comment describing why the use is needed * * This should be used for corner cases where the compiler cannot do the * right thing, or during transitions between APIs, etc. It should be used * very rarely, and includes a place for justification detailing where bounds * checking has happened, and why existing solutions cannot be employed. */ #define unsafe_memcpy(dst, src, bytes, justification) \ __underlying_memcpy(dst, src, bytes) /* * Clang's use of __builtin_*object_size() within inlines needs hinting via * __pass_*object_size(). The preference is to only ever use type 1 (member * size, rather than struct size), but there remain some stragglers using * type 0 that will be converted in the future. */ #if __has_builtin(__builtin_dynamic_object_size) #define POS __pass_dynamic_object_size(1) #define POS0 __pass_dynamic_object_size(0) #else #define POS __pass_object_size(1) #define POS0 __pass_object_size(0) #endif #define __compiletime_lessthan(bounds, length) ( \ __builtin_constant_p((bounds) < (length)) && \ (bounds) < (length) \ ) /** * strncpy - Copy a string to memory with non-guaranteed NUL padding * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * @size: bytes to write at @p * * If strlen(@q) >= @size, the copy of @q will stop after @size bytes, * and @p will NOT be NUL-terminated * * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes * will be written to @p until @size total bytes have been written. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * over-reads of @q, it cannot defend against writing unterminated * results to @p. Using strncpy() remains ambiguous and fragile. * Instead, please choose an alternative, so that the expectation * of @p's contents is unambiguous: * * +--------------------+--------------------+------------+ * | **p** needs to be: | padded to **size** | not padded | * +====================+====================+============+ * | NUL-terminated | strscpy_pad() | strscpy() | * +--------------------+--------------------+------------+ * | not NUL-terminated | strtomem_pad() | strtomem() | * +--------------------+--------------------+------------+ * * Note strscpy*()'s differing return values for detecting truncation, * and strtomem*()'s expectation that the destination is marked with * __nonstring when it is a character array. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { const size_t p_size = __member_size(p); if (__compiletime_lessthan(p_size, size)) __write_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_strncpy, FORTIFY_WRITE, p_size, size, p); return __underlying_strncpy(p, q, size); } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); /** * strnlen - Return bounded count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * @maxlen: maximum number of characters to count. * * Returns number of characters in @p (NOT including the final NUL), or * @maxlen, if no NUL has been found up to there. * */ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { const size_t p_size = __member_size(p); const size_t p_len = __compiletime_strlen(p); size_t ret; /* We can take compile-time actions when maxlen is const. */ if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) { /* If p is const, we can use its compile-time-known len. */ if (maxlen >= p_size) return p_len; } /* Do not check characters beyond the end of p. */ ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(FORTIFY_FUNC_strnlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* * Defined after fortified strnlen to reuse it. However, it must still be * possible for strlen() to be used on compile-time strings for use in * static initializers (i.e. as a constant expression). */ /** * strlen - Return count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * * Do not use this function unless the string length is known at * compile-time. When @p is unterminated, this function may crash * or return unexpected counts that could lead to memory content * exposures. Prefer strnlen(). * * Returns number of characters in @p (NOT including the final NUL). * */ #define strlen(p) \ __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ __builtin_strlen(p), __fortify_strlen(p)) __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) __kernel_size_t __fortify_strlen(const char * const POS p) { const size_t p_size = __member_size(p); __kernel_size_t ret; /* Give up if we don't know how large p is. */ if (p_size == SIZE_MAX) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(FORTIFY_FUNC_strlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* Defined after fortified strnlen() to reuse it. */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy); __FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size) { /* Use string size rather than possible enclosing struct size. */ const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t len; /* If we cannot get size of p and q default to call strscpy. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strscpy(p, q, size); /* * If size can be known at compile time and is greater than * p_size, generate a compile time write overflow error. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Short-circuit for compile-time known-safe lengths. */ if (__compiletime_lessthan(p_size, SIZE_MAX)) { len = __compiletime_strlen(q); if (len < SIZE_MAX && __compiletime_lessthan(len, size)) { __underlying_memcpy(p, q, len + 1); return len; } } /* * This call protects from read overflow, because len will default to q * length if it smaller than size. */ len = strnlen(q, size); /* * If len equals size, we will copy only size bytes which leads to * -E2BIG being returned. * Otherwise we will copy len + 1 because of the final '\O'. */ len = len == size ? size : len + 1; /* * Generate a runtime write overflow error if len is greater than * p_size. */ if (p_size < len) fortify_panic(FORTIFY_FUNC_strscpy, FORTIFY_WRITE, p_size, len, -E2BIG); /* * We can now safely call vanilla strscpy because we are protected from: * 1. Read overflow thanks to call to strnlen(). * 2. Write overflow thanks to above ifs. */ return __real_strscpy(p, q, len); } /* Defined after fortified strlen() to reuse it. */ extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat); /** * strlcat - Append a string to an existing string * * @p: pointer to %NUL-terminated string to append to * @q: pointer to %NUL-terminated string to append from * @avail: Maximum bytes available in @p * * Appends %NUL-terminated string @q after the %NUL-terminated * string at @p, but will not write beyond @avail bytes total, * potentially truncating the copy from @q. @p will stay * %NUL-terminated only if a %NUL already existed within * the @avail bytes of @p. If so, the resulting number of * bytes copied from @q will be at most "@avail - strlen(@p) - 1". * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf(), seq_buf, or similar. * * Returns total bytes that _would_ have been contained by @p * regardless of truncation, similar to snprintf(). If return * value is >= @avail, the string has been truncated. * */ __FORTIFY_INLINE size_t strlcat(char * const POS p, const char * const POS q, size_t avail) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len; size_t actual, wanted; /* Give up immediately if both buffer sizes are unknown. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strlcat(p, q, avail); p_len = strnlen(p, avail); copy_len = strlen(q); wanted = actual = p_len + copy_len; /* Cannot append any more: report truncation. */ if (avail <= p_len) return wanted; /* Give up if string is already overflowed. */ if (p_size <= p_len) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_READ, p_size, p_len + 1, wanted); if (actual >= avail) { copy_len = avail - p_len - 1; actual = p_len + copy_len; } /* Give up if copy will overflow. */ if (p_size <= actual) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_WRITE, p_size, actual + 1, wanted); __underlying_memcpy(p + p_len, q, copy_len); p[actual] = '\0'; return wanted; } /* Defined after fortified strlcat() to reuse it. */ /** * strcat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to NUL-terminated source string to append from * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the * destination buffer size is known to the compiler. Prefer * building the string with formatting, via scnprintf() or similar. * At the very least, use strncat(). * * Returns @p. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) char *strcat(char * const POS p, const char *q) { const size_t p_size = __member_size(p); const size_t wanted = strlcat(p, q, p_size); if (p_size <= wanted) fortify_panic(FORTIFY_FUNC_strcat, FORTIFY_WRITE, p_size, wanted + 1, p); return p; } /** * strncat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to source string to append from * @count: Maximum bytes to read from @q * * Appends at most @count bytes from @q (stopping at the first * NUL byte) after the NUL-terminated string at @p. @p will be * NUL-terminated. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf() or similar. * * Returns @p. * */ /* Defined after fortified strlen() and strnlen() to reuse them. */ __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len, total; if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); total = p_len + copy_len + 1; if (p_size < total) fortify_panic(FORTIFY_FUNC_strncat, FORTIFY_WRITE, p_size, total, p); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE bool fortify_memset_chk(__kernel_size_t size, const size_t p_size, const size_t p_size_field) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); /* Warn when write size is larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(FORTIFY_FUNC_memset, FORTIFY_WRITE, p_size, size, true); return false; } #define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ size_t __fortify_size = (size_t)(size); \ fortify_memset_chk(__fortify_size, p_size, p_size_field), \ __underlying_memset(p, c, __fortify_size); \ }) /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #ifndef CONFIG_KMSAN #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ __struct_size(p), __member_size(p)) #endif /* * To make sure the compiler can enforce protection against buffer overflows, * memcpy(), memmove(), and memset() must not be used beyond individual * struct members. If you need to copy across multiple members, please use * struct_group() to create a named mirror of an anonymous struct union. * (e.g. see struct sk_buff.) Read overflow checking is currently only * done when a write overflow is also present, or when building with W=1. * * Mitigation coverage matrix * Bounds checking at: * +-------+-------+-------+-------+ * | Compile time | Run time | * memcpy() argument sizes: | write | read | write | read | * dest source length +-------+-------+-------+-------+ * memcpy(known, known, constant) | y | y | n/a | n/a | * memcpy(known, unknown, constant) | y | n | n/a | V | * memcpy(known, known, dynamic) | n | n | B | B | * memcpy(known, unknown, dynamic) | n | n | B | V | * memcpy(unknown, known, constant) | n | y | V | n/a | * memcpy(unknown, unknown, constant) | n | n | V | V | * memcpy(unknown, known, dynamic) | n | n | V | B | * memcpy(unknown, unknown, dynamic) | n | n | V | V | * +-------+-------+-------+-------+ * * y = perform deterministic compile-time bounds checking * n = cannot perform deterministic compile-time bounds checking * n/a = no run-time bounds checking needed since compile-time deterministic * B = can perform run-time bounds checking (currently unimplemented) * V = vulnerable to run-time overflow (will need refactoring to solve) * */ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t p_size, const size_t q_size, const size_t p_size_field, const size_t q_size_field, const u8 func) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); if (__compiletime_lessthan(q_size_field, q_size) && __compiletime_lessthan(q_size, size)) __read_overflow2(); /* Warn when write size argument larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); /* * Warn for source field over-read when building with W=1 * or when an over-write happened, so both can be fixed at * the same time. */ if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || __compiletime_lessthan(p_size_field, size)) && __compiletime_lessthan(q_size_field, size)) __read_overflow2_field(q_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(func, FORTIFY_WRITE, p_size, size, true); else if (q_size != SIZE_MAX && q_size < size) fortify_panic(func, FORTIFY_READ, p_size, size, true); /* * Warn when writing beyond destination field size. * * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be * detected at compile-time (as can be done when the destination * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; return false; } /* * To work around what seems to be an optimizer bug, the macro arguments * need to have const copies or the values end up changed by the time they * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture * __bos() results in const temp vars") for more details. */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ const size_t __p_size = (p_size); \ const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ /* Keep a mutable version of the size for the final copy. */ \ size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ /* Hide only the run-time size from value range tracking to */ \ /* silence compile-time false positive bounds warnings. */ \ if (!__builtin_constant_p(__copy_size)) \ OPTIMIZER_HIDE_VAR(__copy_size); \ __underlying_##op(p, q, __copy_size); \ }) /* * Notes about compile-time buffer size detection: * * With these types... * * struct middle { * u16 a; * u8 middle_buf[16]; * int b; * }; * struct end { * u16 a; * u8 end_buf[16]; * }; * struct flex { * int a; * u8 flex_buf[]; * }; * * void func(TYPE *ptr) { ... } * * Cases where destination size cannot be currently detected: * - the size of ptr's object (seemingly by design, gcc & clang fail): * __builtin_object_size(ptr, 1) == SIZE_MAX * - the size of flexible arrays in ptr's obj (by design, dynamic size): * __builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX * - the size of ANY array at the end of ptr's obj (gcc and clang bug): * __builtin_object_size(ptr->end_buf, 1) == SIZE_MAX * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836 * * Cases where destination size is currently detected: * - the size of non-array members within ptr's object: * __builtin_object_size(ptr->a, 1) == 2 * - the size of non-flexible-array in the middle of ptr's obj: * __builtin_object_size(ptr->middle_buf, 1) == 16 * */ /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memcpy) #define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memscan, FORTIFY_READ, p_size, size, NULL); return __real_memscan(p, c, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { const size_t p_size = __struct_size(p); const size_t q_size = __struct_size(q); if (__builtin_constant_p(size)) { if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (__compiletime_lessthan(q_size, size)) __read_overflow2(); } if (p_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, p_size, size, INT_MIN); else if (q_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, q_size, size, INT_MIN); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr, FORTIFY_READ, p_size, size, NULL); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr_inv, FORTIFY_READ, p_size, size, NULL); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); __FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } #define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * * Do not use this function. While FORTIFY_SOURCE tries to avoid * overflows, this is only possible when the sizes of @q and @p are * known to the compiler. Prefer strscpy(), though note its different * return values for detecting truncation. * * Returns @p. * */ /* Defined after fortified strlen to reuse it. */ __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) char *strcpy(char * const POS p, const char * const POS q) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t size; /* If neither buffer size is known, immediately give up. */ if (__builtin_constant_p(p_size) && __builtin_constant_p(q_size) && p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strcpy(p, q); size = strlen(q) + 1; /* Compile-time check for const size overflow. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(FORTIFY_FUNC_strcpy, FORTIFY_WRITE, p_size, size, p); __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #undef POS #undef POS0 #endif /* _LINUX_FORTIFY_STRING_H_ */ |
| 43 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netclassid_cgroup.c Classid Cgroupfs Handling * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/slab.h> #include <linux/cgroup.h> #include <linux/fdtable.h> #include <linux/sched/task.h> #include <net/cls_cgroup.h> #include <net/sock.h> static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cgroup_cls_state, css) : NULL; } struct cgroup_cls_state *task_cls_state(struct task_struct *p) { return css_cls_state(task_css_check(p, net_cls_cgrp_id, rcu_read_lock_held() || rcu_read_lock_bh_held() || rcu_read_lock_trace_held())); } EXPORT_SYMBOL_GPL(task_cls_state); static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_cls_state *cs; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); return &cs->css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_cls_state *cs = css_cls_state(css); struct cgroup_cls_state *parent = css_cls_state(css->parent); if (parent) cs->classid = parent->classid; return 0; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css_cls_state(css)); } /* * To avoid freezing of sockets creation for tasks with big number of threads * and opened sockets lets release file_lock every 1000 iterated descriptors. * New sockets will already have been created with new classid. */ struct update_classid_context { u32 classid; unsigned int batch; }; #define UPDATE_CLASSID_BATCH 1000 static int update_classid_sock(const void *v, struct file *file, unsigned int n) { struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); if (--ctx->batch == 0) { ctx->batch = UPDATE_CLASSID_BATCH; return n + 1; } return 0; } static void update_classid_task(struct task_struct *p, u32 classid) { struct update_classid_context ctx = { .classid = classid, .batch = UPDATE_CLASSID_BATCH }; unsigned int fd = 0; /* Only update the leader task, when many threads in this task, * so it can avoid the useless traversal. */ if (p != p->group_leader) return; do { task_lock(p); fd = iterate_fd(p->files, fd, update_classid_sock, &ctx); task_unlock(p); cond_resched(); } while (fd); } static void cgrp_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct task_struct *p; cgroup_taskset_for_each(p, css, tset) { update_classid_task(p, css_cls_state(css)->classid); } } static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) { return css_cls_state(css)->classid; } static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, u64 value) { struct cgroup_cls_state *cs = css_cls_state(css); struct css_task_iter it; struct task_struct *p; cs->classid = (u32)value; css_task_iter_start(css, 0, &it); while ((p = css_task_iter_next(&it))) update_classid_task(p, cs->classid); css_task_iter_end(&it); return 0; } static struct cftype ss_files[] = { { .name = "classid", .read_u64 = read_classid, .write_u64 = write_classid, }, { } /* terminate */ }; struct cgroup_subsys net_cls_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = cgrp_attach, .legacy_cftypes = ss_files, }; |
| 22 2 1 2 2 2 2 2 9 9 9 20 20 9 3 1 1 1 2 2 2 2 2 2 2 1 1 4 1 1 1 1 2 4 3 1 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_region { struct devlink *devlink; struct devlink_port *port; struct list_head list; union { const struct devlink_region_ops *ops; const struct devlink_port_region_ops *port_ops; }; struct mutex snapshot_lock; /* protects snapshot_list, * max_snapshots and cur_snapshots * consistency. */ struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; u64 size; }; struct devlink_snapshot { struct list_head list; struct devlink_region *region; u8 *data; u32 id; }; static struct devlink_region * devlink_region_get_by_name(struct devlink *devlink, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_region * devlink_port_region_get_by_name(struct devlink_port *port, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &port->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { struct devlink_snapshot *snapshot; list_for_each_entry(snapshot, ®ion->snapshot_list, list) if (snapshot->id == id) return snapshot; return NULL; } static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) { struct nlattr *snap_attr; int err; snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); if (!snap_attr) return -EMSGSIZE; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto nla_put_failure; nla_nest_end(msg, snap_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snap_attr); return err; } static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_region *region) { struct devlink_snapshot *snapshot; struct nlattr *snapshots_attr; int err; snapshots_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); if (!snapshots_attr) return -EMSGSIZE; list_for_each_entry(snapshot, ®ion->snapshot_list, list) { err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); if (err) goto nla_put_failure; } nla_nest_end(msg, snapshots_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snapshots_attr); return err; } static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct devlink_region *region) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto nla_put_failure; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, region->max_snapshots); if (err) goto nla_put_failure; err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } static struct sk_buff * devlink_nl_region_notify_build(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd, u32 portid, u32 seq) { struct devlink *devlink = region->devlink; struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); if (!hdr) { err = -EMSGSIZE; goto out_free_msg; } err = devlink_nl_put_handle(msg, devlink); if (err) goto out_cancel_msg; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto out_cancel_msg; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto out_cancel_msg; if (snapshot) { err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto out_cancel_msg; } else { err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto out_cancel_msg; } genlmsg_end(msg, hdr); return msg; out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ERR_PTR(err); } static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; devlink_nl_notify_send(devlink, msg); } void devlink_regions_notify_register(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); } void devlink_regions_notify_unregister(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry_reverse(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); } /** * __devlink_snapshot_id_increment - Increment number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a new snapshot begins using an id. Load the count for the * given id from the snapshot xarray, increment it, and store it back. * * Called when a new snapshot is created with the given id. * * The id *must* have been previously allocated by * devlink_region_snapshot_id_get(). * * Returns 0 on success, or an error on failure. */ static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) { unsigned long count; void *p; int err; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) { err = -EINVAL; goto unlock; } if (WARN_ON(!xa_is_value(p))) { err = -EINVAL; goto unlock; } count = xa_to_value(p); count++; err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC)); unlock: xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a snapshot is deleted and stops using an id. Load the count * for the given id from the snapshot xarray, decrement it, and store it * back. * * If the count reaches zero, erase this id from the xarray, freeing it * up for future re-use by devlink_region_snapshot_id_get(). * * Called when a snapshot using the given id is deleted, and when the * initial allocator of the id is finished using it. */ static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) { unsigned long count; void *p; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) goto unlock; if (WARN_ON(!xa_is_value(p))) goto unlock; count = xa_to_value(p); if (count > 1) { count--; __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC); } else { /* If this was the last user, we can erase this id */ __xa_erase(&devlink->snapshot_ids, id); } unlock: xa_unlock(&devlink->snapshot_ids); } /** * __devlink_snapshot_id_insert - Insert a specific snapshot ID * @devlink: devlink instance * @id: the snapshot id * * Mark the given snapshot id as used by inserting a zero value into the * snapshot xarray. * * This must be called while holding the devlink instance lock. Unlike * devlink_snapshot_id_get, the initial reference count is zero, not one. * It is expected that the id will immediately be used before * releasing the devlink instance lock. * * Returns zero on success, or an error code if the snapshot id could not * be inserted. */ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { int err; xa_lock(&devlink->snapshot_ids); if (xa_load(&devlink->snapshot_ids, id)) { xa_unlock(&devlink->snapshot_ids); return -EEXIST; } err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), GFP_ATOMIC)); xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_region_snapshot_id_get - get snapshot ID * @devlink: devlink instance * @id: storage to return snapshot id * * Allocates a new snapshot id. Returns zero on success, or a negative * error on failure. Must be called while holding the devlink instance * lock. * * Snapshot IDs are tracked using an xarray which stores the number of * users of the snapshot id. * * Note that the caller of this function counts as a 'user', in order to * avoid race conditions. The caller must release its hold on the * snapshot by using devlink_region_snapshot_id_put. */ static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), xa_limit_32b, GFP_KERNEL); } /** * __devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * Must be called only while holding the region snapshot lock. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ static int __devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot; int err; lockdep_assert_held(®ion->snapshot_lock); /* check if region can hold one more snapshot */ if (region->cur_snapshots == region->max_snapshots) return -ENOSPC; if (devlink_region_snapshot_get_by_id(region, snapshot_id)) return -EEXIST; snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); if (!snapshot) return -ENOMEM; err = __devlink_snapshot_id_increment(devlink, snapshot_id); if (err) goto err_snapshot_id_increment; snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; list_add_tail(&snapshot->list, ®ion->snapshot_list); region->cur_snapshots++; devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); return 0; err_snapshot_id_increment: kfree(snapshot); return err; } static void devlink_region_snapshot_del(struct devlink_region *region, struct devlink_snapshot *snapshot) { struct devlink *devlink = region->devlink; lockdep_assert_held(®ion->snapshot_lock); devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); region->cur_snapshots--; list_del(&snapshot->list); region->ops->destructor(snapshot->data); __devlink_snapshot_id_decrement(devlink, snapshot->id); kfree(snapshot); } int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; unsigned int index; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) return -EINVAL; if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, info->snd_portid, info->snd_seq, 0, region); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, struct netlink_callback *cb, struct devlink_port *port, int *idx, int start, int flags) { struct devlink_region *region; int err = 0; list_for_each_entry(region, &port->region_list, list) { if (*idx < start) { (*idx)++; continue; } err = devlink_nl_region_fill(msg, port->devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) goto out; (*idx)++; } out: return err; } static int devlink_nl_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; list_for_each_entry(region, &devlink->region_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) { state->idx = idx; return err; } idx++; } xa_for_each(&devlink->ports, port_index, port) { err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, state->idx, flags); if (err) { state->idx = idx; return err; } } return 0; } int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) return -EINVAL; region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; mutex_lock(®ion->snapshot_lock); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { mutex_unlock(®ion->snapshot_lock); return -EINVAL; } devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); return 0; } int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; u8 *data; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { NL_SET_ERR_MSG(info->extack, "No region name provided"); return -EINVAL; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG(info->extack, "The requested region does not exist"); return -EINVAL; } if (!region->ops->snapshot) { NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot"); return -EOPNOTSUPP; } mutex_lock(®ion->snapshot_lock); if (region->cur_snapshots == region->max_snapshots) { NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots"); err = -ENOSPC; goto unlock; } snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (snapshot_id_attr) { snapshot_id = nla_get_u32(snapshot_id_attr); if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use"); err = -EEXIST; goto unlock; } err = __devlink_snapshot_id_insert(devlink, snapshot_id); if (err) goto unlock; } else { err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); if (err) { NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id"); goto unlock; } } if (port) err = region->port_ops->snapshot(port, region->port_ops, info->extack, &data); else err = region->ops->snapshot(devlink, region->ops, info->extack, &data); if (err) goto err_snapshot_capture; err = __devlink_region_snapshot_create(region, data, snapshot_id); if (err) goto err_snapshot_create; if (!snapshot_id_attr) { struct sk_buff *msg; snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (WARN_ON(!snapshot)) { err = -EINVAL; goto unlock; } msg = devlink_nl_region_notify_build(region, snapshot, DEVLINK_CMD_REGION_NEW, info->snd_portid, info->snd_seq); err = PTR_ERR_OR_ZERO(msg); if (err) goto err_notify; err = genlmsg_reply(msg, info); if (err) goto err_notify; } mutex_unlock(®ion->snapshot_lock); return 0; err_snapshot_create: region->ops->destructor(data); err_snapshot_capture: __devlink_snapshot_id_decrement(devlink, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; err_notify: devlink_region_snapshot_del(region, snapshot); unlock: mutex_unlock(®ion->snapshot_lock); return err; } static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, u8 *chunk, u32 chunk_size, u64 addr) { struct nlattr *chunk_attr; int err; chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); if (!chunk_attr) return -EINVAL; err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr); if (err) goto nla_put_failure; nla_nest_end(msg, chunk_attr); return 0; nla_put_failure: nla_nest_cancel(msg, chunk_attr); return err; } #define DEVLINK_REGION_READ_CHUNK_SIZE 256 typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack); static int devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb, void *cb_priv, u64 start_offset, u64 end_offset, u64 *new_offset, struct netlink_ext_ack *extack) { u64 curr_offset = start_offset; int err = 0; u8 *data; /* Allocate and re-use a single buffer */ data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL); if (!data) return -ENOMEM; *new_offset = start_offset; while (curr_offset < end_offset) { u32 data_size; data_size = min_t(u32, end_offset - curr_offset, DEVLINK_REGION_READ_CHUNK_SIZE); err = cb(cb_priv, data, data_size, curr_offset, extack); if (err) break; err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset); if (err) break; curr_offset += data_size; } *new_offset = curr_offset; kfree(data); return err; } static int devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack __always_unused *extack) { struct devlink_snapshot *snapshot = cb_priv; memcpy(chunk, &snapshot->data[curr_offset], chunk_size); return 0; } static int devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->port_ops->read(region->port, region->port_ops, extack, curr_offset, chunk_size, chunk); } static int devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->ops->read(region->devlink, region->ops, extack, curr_offset, chunk_size, chunk); } int devlink_nl_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; void *region_cb_priv; void *hdr; int err; start_offset = state->start_offset; devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); if (!attrs[DEVLINK_ATTR_REGION_NAME]) { NL_SET_ERR_MSG(cb->extack, "No region name provided"); err = -EINVAL; goto out_unlock; } if (attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { err = -ENODEV; goto out_unlock; } } region_attr = attrs[DEVLINK_ATTR_REGION_NAME]; region_name = nla_data(region_attr); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist"); err = -EINVAL; goto out_unlock; } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (!snapshot_attr) { if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); err = -EINVAL; goto out_unlock; } if (!region->ops->read) { NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); err = -EOPNOTSUPP; goto out_unlock; } if (port) region_cb = &devlink_region_port_direct_fill; else region_cb = &devlink_region_direct_fill; region_cb_priv = region; } else { struct devlink_snapshot *snapshot; u32 snapshot_id; if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); err = -EINVAL; goto out_unlock; } snapshot_id = nla_get_u32(snapshot_attr); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); err = -EINVAL; goto out_unlock; } region_cb = &devlink_region_snapshot_fill; region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { if (!start_offset) start_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); } if (end_offset > region->size) end_offset = region->size; /* return 0 if there is no further data to read */ if (start_offset == end_offset) { err = 0; goto out_unlock; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); if (!hdr) { err = -EMSGSIZE; goto out_unlock; } err = devlink_nl_put_handle(skb, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); if (!chunks_attr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, start_offset, end_offset, &ret_offset, cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ if (ret_offset == start_offset) { err = -EINVAL; goto nla_put_failure; } state->start_offset = ret_offset; nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); devl_unlock(devlink); devlink_put(devlink); return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: devl_unlock(devlink); devlink_put(devlink); return err; } /** * devl_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region */ struct devlink_region *devl_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_assert_locked(devlink); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); if (devlink_region_get_by_name(devlink, ops->name)) return ERR_PTR(-EEXIST); region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) return ERR_PTR(-ENOMEM); region->devlink = devlink; region->max_snapshots = region_max_snapshots; region->ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &devlink->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); return region; } EXPORT_SYMBOL_GPL(devl_region_create); /** * devlink_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_lock(devlink); region = devl_region_create(devlink, ops, region_max_snapshots, region_size); devl_unlock(devlink); return region; } EXPORT_SYMBOL_GPL(devlink_region_create); /** * devlink_port_region_create - create a new address region for a port * * @port: devlink port * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_port_region_create(struct devlink_port *port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink *devlink = port->devlink; struct devlink_region *region; int err = 0; ASSERT_DEVLINK_PORT_INITIALIZED(port); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); devl_lock(devlink); if (devlink_port_region_get_by_name(port, ops->name)) { err = -EEXIST; goto unlock; } region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) { err = -ENOMEM; goto unlock; } region->devlink = devlink; region->port = port; region->max_snapshots = region_max_snapshots; region->port_ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &port->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); devl_unlock(devlink); return region; unlock: devl_unlock(devlink); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(devlink_port_region_create); /** * devl_region_destroy - destroy address region * * @region: devlink region to destroy */ void devl_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot, *ts; devl_assert_locked(devlink); /* Free all snapshots of region */ mutex_lock(®ion->snapshot_lock); list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); list_del(®ion->list); mutex_destroy(®ion->snapshot_lock); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); kfree(region); } EXPORT_SYMBOL_GPL(devl_region_destroy); /** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy * * Context: Takes and release devlink->lock <mutex>. */ void devlink_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; devl_lock(devlink); devl_region_destroy(region); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_region_destroy); /** * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken * on multiple regions at the same time/by the same trigger. * * The caller of this function must use devlink_region_snapshot_id_put * when finished creating regions using this id. * * Returns zero on success, or a negative error code on failure. * * @devlink: devlink * @id: storage to return id */ int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return __devlink_region_snapshot_id_get(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_id_put - put snapshot ID reference * * This should be called by a driver after finishing creating snapshots * with an id. Doing so ensures that the ID can later be released in the * event that all snapshots using it have been destroyed. * * @devlink: devlink * @id: id to release reference on */ void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) { __devlink_snapshot_id_decrement(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); /** * devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { int err; mutex_lock(®ion->snapshot_lock); err = __devlink_region_snapshot_create(region, data, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); |
| 1 2331 1 2323 2128 2331 2124 2323 3312 41 39 389 386 619 833 620 830 4069 1267 2636 2629 2405 2530 41 39 40 41 39 40 28 39 340 337 710 3772 380 3491 454 252 150 4233 4234 3092 3784 714 409 264 249 408 41 381 381 8 2 305 307 2 306 307 307 9 9 9 1 8 8 1193 1523 1197 4226 365 3897 565 565 3 419 145 144 115 33 624 624 623 442 362 84 82 566 564 565 3708 30 2642 1133 2629 1070 4091 2 134 2 2 4 4223 8 4224 4225 566 3712 4241 41 4240 4253 4225 4249 378 379 1 1 2 3 1 1 379 379 1 3 104 1 290 1 2 12 13 13 12 12 13 367 379 375 4 3 376 2 5 375 367 367 39 1 23 14 2 2 2 5 4 3 1 6 26 22 24 23 8 26 37 36 36 36 1 1 9 35 32 11 10 37 15 30 6 36 13 31 30 3 19 19 5 16 16 16 16 15 12 14 13 13 14 6 6 6 6 3 4 146 146 42 42 42 4 41 41 2 42 42 76 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Generic Netlink Family * * Authors: Jamal Hadi Salim * Thomas Graf <tgraf@suug.ch> * Johannes Berg <johannes@sipsolutions.net> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/string_helpers.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> #include <linux/rwsem.h> #include <linux/idr.h> #include <net/sock.h> #include <net/genetlink.h> #include "genetlink.h" static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); void genl_lock(void) { mutex_lock(&genl_mutex); } EXPORT_SYMBOL(genl_lock); void genl_unlock(void) { mutex_unlock(&genl_mutex); } EXPORT_SYMBOL(genl_unlock); static void genl_lock_all(void) { down_write(&cb_lock); genl_lock(); } static void genl_unlock_all(void) { genl_unlock(); up_write(&cb_lock); } static void genl_op_lock(const struct genl_family *family) { if (!family->parallel_ops) genl_lock(); } static void genl_op_unlock(const struct genl_family *family) { if (!family->parallel_ops) genl_unlock(); } static DEFINE_IDR(genl_fam_idr); /* * Bitmap of multicast groups that are currently in use. * * To avoid an allocation at boot of just one unsigned long, * declare it global instead. * Bit 0 is marked as already used since group 0 is invalid. * Bit 1 is marked as already used since the drop-monitor code * abuses the API and thinks it can statically use group 1. * That group will typically conflict with other groups that * any proper users use. * Bit 16 is marked as used since it's used for generic netlink * and the code no longer marks pre-reserved IDs as used. * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. * Bit 18 is marked as already used since the PMCRAID driver * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | BIT(GENL_ID_VFS_DQUOT) | BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; /* We need the last attribute with non-zero ID therefore a 2-entry array */ static struct nla_policy genl_policy_reject_all[] = { { .type = NLA_REJECT }, { .type = NLA_REJECT }, }; static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); static void genl_op_fill_in_reject_policy(const struct genl_family *family, struct genl_ops *op) { BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1); if (op->policy || op->cmd < family->resv_start_op) return; op->policy = genl_policy_reject_all; op->maxattr = 1; } static void genl_op_fill_in_reject_policy_split(const struct genl_family *family, struct genl_split_ops *op) { if (op->policy) return; op->policy = genl_policy_reject_all; op->maxattr = 1; } static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); } static const struct genl_family *genl_family_find_byname(char *name) { const struct genl_family *family; unsigned int id; idr_for_each_entry(&genl_fam_idr, family, id) if (strcmp(family->name, name) == 0) return family; return NULL; } struct genl_op_iter { const struct genl_family *family; struct genl_split_ops doit; struct genl_split_ops dumpit; int cmd_idx; int entry_idx; u32 cmd; u8 flags; }; static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) { *op = family->ops[i]; if (!op->maxattr) op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_ops; i++) if (family->ops[i].cmd == cmd) { genl_op_from_full(family, i, op); return 0; } return -ENOENT; } static void genl_op_from_small(const struct genl_family *family, unsigned int i, struct genl_ops *op) { memset(op, 0, sizeof(*op)); op->doit = family->small_ops[i].doit; op->dumpit = family->small_ops[i].dumpit; op->cmd = family->small_ops[i].cmd; op->internal_flags = family->small_ops[i].internal_flags; op->flags = family->small_ops[i].flags; op->validate = family->small_ops[i].validate; op->maxattr = family->maxattr; op->policy = family->policy; genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_small_ops; i++) if (family->small_ops[i].cmd == cmd) { genl_op_from_small(family, i, op); return 0; } return -ENOENT; } static void genl_op_from_split(struct genl_op_iter *iter) { const struct genl_family *family = iter->family; int i, cnt = 0; i = iter->entry_idx - family->n_ops - family->n_small_ops; if (family->split_ops[i + cnt].flags & GENL_CMD_CAP_DO) { iter->doit = family->split_ops[i + cnt]; genl_op_fill_in_reject_policy_split(family, &iter->doit); cnt++; } else { memset(&iter->doit, 0, sizeof(iter->doit)); } if (i + cnt < family->n_split_ops && family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP && (!cnt || family->split_ops[i + cnt].cmd == iter->doit.cmd)) { iter->dumpit = family->split_ops[i + cnt]; genl_op_fill_in_reject_policy_split(family, &iter->dumpit); cnt++; } else { memset(&iter->dumpit, 0, sizeof(iter->dumpit)); } WARN_ON(!cnt); iter->entry_idx += cnt; } static int genl_get_cmd_split(u32 cmd, u8 flag, const struct genl_family *family, struct genl_split_ops *op) { int i; for (i = 0; i < family->n_split_ops; i++) if (family->split_ops[i].cmd == cmd && family->split_ops[i].flags & flag) { *op = family->split_ops[i]; return 0; } return -ENOENT; } static int genl_cmd_full_to_split(struct genl_split_ops *op, const struct genl_family *family, const struct genl_ops *full, u8 flags) { if ((flags & GENL_CMD_CAP_DO && !full->doit) || (flags & GENL_CMD_CAP_DUMP && !full->dumpit)) { memset(op, 0, sizeof(*op)); return -ENOENT; } if (flags & GENL_CMD_CAP_DUMP) { op->start = full->start; op->dumpit = full->dumpit; op->done = full->done; } else { op->pre_doit = family->pre_doit; op->doit = full->doit; op->post_doit = family->post_doit; } if (flags & GENL_CMD_CAP_DUMP && full->validate & GENL_DONT_VALIDATE_DUMP) { op->policy = NULL; op->maxattr = 0; } else { op->policy = full->policy; op->maxattr = full->maxattr; } op->cmd = full->cmd; op->internal_flags = full->internal_flags; op->flags = full->flags; op->validate = full->validate; /* Make sure flags include the GENL_CMD_CAP_DO / GENL_CMD_CAP_DUMP */ op->flags |= flags; return 0; } /* Must make sure that op is initialized to 0 on failure */ static int genl_get_cmd(u32 cmd, u8 flags, const struct genl_family *family, struct genl_split_ops *op) { struct genl_ops full; int err; err = genl_get_cmd_full(cmd, family, &full); if (err == -ENOENT) err = genl_get_cmd_small(cmd, family, &full); /* Found one of legacy forms */ if (err == 0) return genl_cmd_full_to_split(op, family, &full, flags); err = genl_get_cmd_split(cmd, flags, family, op); if (err) memset(op, 0, sizeof(*op)); return err; } /* For policy dumping only, get ops of both do and dump. * Fail if both are missing, genl_get_cmd() will zero-init in case of failure. */ static int genl_get_cmd_both(u32 cmd, const struct genl_family *family, struct genl_split_ops *doit, struct genl_split_ops *dumpit) { int err1, err2; err1 = genl_get_cmd(cmd, GENL_CMD_CAP_DO, family, doit); err2 = genl_get_cmd(cmd, GENL_CMD_CAP_DUMP, family, dumpit); return err1 && err2 ? -ENOENT : 0; } static bool genl_op_iter_init(const struct genl_family *family, struct genl_op_iter *iter) { iter->family = family; iter->cmd_idx = 0; iter->entry_idx = 0; iter->flags = 0; return iter->family->n_ops + iter->family->n_small_ops + iter->family->n_split_ops; } static bool genl_op_iter_next(struct genl_op_iter *iter) { const struct genl_family *family = iter->family; bool legacy_op = true; struct genl_ops op; if (iter->entry_idx < family->n_ops) { genl_op_from_full(family, iter->entry_idx, &op); } else if (iter->entry_idx < family->n_ops + family->n_small_ops) { genl_op_from_small(family, iter->entry_idx - family->n_ops, &op); } else if (iter->entry_idx < family->n_ops + family->n_small_ops + family->n_split_ops) { legacy_op = false; /* updates entry_idx */ genl_op_from_split(iter); } else { return false; } iter->cmd_idx++; if (legacy_op) { iter->entry_idx++; genl_cmd_full_to_split(&iter->doit, family, &op, GENL_CMD_CAP_DO); genl_cmd_full_to_split(&iter->dumpit, family, &op, GENL_CMD_CAP_DUMP); } iter->cmd = iter->doit.cmd | iter->dumpit.cmd; iter->flags = iter->doit.flags | iter->dumpit.flags; return true; } static void genl_op_iter_copy(struct genl_op_iter *dst, struct genl_op_iter *src) { *dst = *src; } static unsigned int genl_op_iter_idx(struct genl_op_iter *iter) { return iter->cmd_idx; } static int genl_allocate_reserve_groups(int n_groups, int *first_id) { unsigned long *new_groups; int start = 0; int i; int id; bool fits; do { if (start == 0) id = find_first_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG); else id = find_next_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG, start); fits = true; for (i = id; i < min_t(int, id + n_groups, mc_groups_longs * BITS_PER_LONG); i++) { if (test_bit(i, mc_groups)) { start = i; fits = false; break; } } if (id + n_groups > mc_groups_longs * BITS_PER_LONG) { unsigned long new_longs = mc_groups_longs + BITS_TO_LONGS(n_groups); size_t nlen = new_longs * sizeof(unsigned long); if (mc_groups == &mc_group_start) { new_groups = kzalloc(nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; *mc_groups = mc_group_start; } else { new_groups = krealloc(mc_groups, nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; for (i = 0; i < BITS_TO_LONGS(n_groups); i++) mc_groups[mc_groups_longs + i] = 0; } mc_groups_longs = new_longs; } } while (!fits); for (i = id; i < id + n_groups; i++) set_bit(i, mc_groups); *first_id = id; return 0; } static struct genl_family genl_ctrl; static int genl_validate_assign_mc_groups(struct genl_family *family) { int first_id; int n_groups = family->n_mcgrps; int err = 0, i; bool groups_allocated = false; if (!n_groups) return 0; for (i = 0; i < n_groups; i++) { const struct genl_multicast_group *grp = &family->mcgrps[i]; if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; if (WARN_ON(!string_is_terminated(grp->name, GENL_NAMSIZ))) return -EINVAL; } /* special-case our own group and hacks */ if (family == &genl_ctrl) { first_id = GENL_ID_CTRL; BUG_ON(n_groups != 1); } else if (strcmp(family->name, "NET_DM") == 0) { first_id = 1; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_VFS_DQUOT) { first_id = GENL_ID_VFS_DQUOT; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_PMCRAID) { first_id = GENL_ID_PMCRAID; BUG_ON(n_groups != 1); } else { groups_allocated = true; err = genl_allocate_reserve_groups(n_groups, &first_id); if (err) return err; } family->mcgrp_offset = first_id; /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; if (family->netnsok) { struct net *net; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { err = __netlink_change_ngroups(net->genl_sock, mc_groups_longs * BITS_PER_LONG); if (err) { /* * No need to roll back, can only fail if * memory allocation fails and then the * number of _possible_ groups has been * increased on some sockets which is ok. */ break; } } rcu_read_unlock(); netlink_table_ungrab(); } else { err = netlink_change_ngroups(init_net.genl_sock, mc_groups_longs * BITS_PER_LONG); } if (groups_allocated && err) { for (i = 0; i < family->n_mcgrps; i++) clear_bit(family->mcgrp_offset + i, mc_groups); } return err; } static void genl_unregister_mc_groups(const struct genl_family *family) { struct net *net; int i; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { for (i = 0; i < family->n_mcgrps; i++) __netlink_clear_multicast_users( net->genl_sock, family->mcgrp_offset + i); } rcu_read_unlock(); netlink_table_ungrab(); for (i = 0; i < family->n_mcgrps; i++) { int grp_id = family->mcgrp_offset + i; if (grp_id != 1) clear_bit(grp_id, mc_groups); genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, &family->mcgrps[i], grp_id); } } static bool genl_split_op_check(const struct genl_split_ops *op) { if (WARN_ON(hweight8(op->flags & (GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP)) != 1)) return true; return false; } static int genl_validate_ops(const struct genl_family *family) { struct genl_op_iter i, j; unsigned int s; if (WARN_ON(family->n_ops && !family->ops) || WARN_ON(family->n_small_ops && !family->small_ops) || WARN_ON(family->n_split_ops && !family->split_ops)) return -EINVAL; for (genl_op_iter_init(family, &i); genl_op_iter_next(&i); ) { if (!(i.flags & (GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP))) return -EINVAL; if (WARN_ON(i.cmd >= family->resv_start_op && (i.doit.validate || i.dumpit.validate))) return -EINVAL; genl_op_iter_copy(&j, &i); while (genl_op_iter_next(&j)) { if (i.cmd == j.cmd) return -EINVAL; } } if (family->n_split_ops) { if (genl_split_op_check(&family->split_ops[0])) return -EINVAL; } for (s = 1; s < family->n_split_ops; s++) { const struct genl_split_ops *a, *b; a = &family->split_ops[s - 1]; b = &family->split_ops[s]; if (genl_split_op_check(b)) return -EINVAL; /* Check sort order */ if (a->cmd < b->cmd) { continue; } else if (a->cmd > b->cmd) { WARN_ON(1); return -EINVAL; } if (a->internal_flags != b->internal_flags || ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP))) { WARN_ON(1); return -EINVAL; } if ((a->flags & GENL_CMD_CAP_DO) && (b->flags & GENL_CMD_CAP_DUMP)) continue; WARN_ON(1); return -EINVAL; } return 0; } static void *genl_sk_priv_alloc(struct genl_family *family) { void *priv; priv = kzalloc(family->sock_priv_size, GFP_KERNEL); if (!priv) return ERR_PTR(-ENOMEM); if (family->sock_priv_init) family->sock_priv_init(priv); return priv; } static void genl_sk_priv_free(const struct genl_family *family, void *priv) { if (family->sock_priv_destroy) family->sock_priv_destroy(priv); kfree(priv); } static int genl_sk_privs_alloc(struct genl_family *family) { if (!family->sock_priv_size) return 0; family->sock_privs = kzalloc(sizeof(*family->sock_privs), GFP_KERNEL); if (!family->sock_privs) return -ENOMEM; xa_init(family->sock_privs); return 0; } static void genl_sk_privs_free(const struct genl_family *family) { unsigned long id; void *priv; if (!family->sock_priv_size) return; xa_for_each(family->sock_privs, id, priv) genl_sk_priv_free(family, priv); xa_destroy(family->sock_privs); kfree(family->sock_privs); } static void genl_sk_priv_free_by_sock(struct genl_family *family, struct sock *sk) { void *priv; if (!family->sock_priv_size) return; priv = xa_erase(family->sock_privs, (unsigned long) sk); if (!priv) return; genl_sk_priv_free(family, priv); } static void genl_release(struct sock *sk, unsigned long *groups) { struct genl_family *family; unsigned int id; down_read(&cb_lock); idr_for_each_entry(&genl_fam_idr, family, id) genl_sk_priv_free_by_sock(family, sk); up_read(&cb_lock); } /** * __genl_sk_priv_get - Get family private pointer for socket, if exists * * @family: family * @sk: socket * * Lookup a private memory for a Generic netlink family and specified socket. * * Caller should make sure this is called in RCU read locked section. * * Return: valid pointer on success, otherwise negative error value * encoded by ERR_PTR(), NULL in case priv does not exist. */ void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk) { if (WARN_ON_ONCE(!family->sock_privs)) return ERR_PTR(-EINVAL); return xa_load(family->sock_privs, (unsigned long) sk); } /** * genl_sk_priv_get - Get family private pointer for socket * * @family: family * @sk: socket * * Lookup a private memory for a Generic netlink family and specified socket. * Allocate the private memory in case it was not already done. * * Return: valid pointer on success, otherwise negative error value * encoded by ERR_PTR(). */ void *genl_sk_priv_get(struct genl_family *family, struct sock *sk) { void *priv, *old_priv; priv = __genl_sk_priv_get(family, sk); if (priv) return priv; /* priv for the family does not exist so far, create it. */ priv = genl_sk_priv_alloc(family); if (IS_ERR(priv)) return ERR_CAST(priv); old_priv = xa_cmpxchg(family->sock_privs, (unsigned long) sk, NULL, priv, GFP_KERNEL); if (old_priv) { genl_sk_priv_free(family, priv); if (xa_is_err(old_priv)) return ERR_PTR(xa_err(old_priv)); /* Race happened, priv for the socket was already inserted. */ return old_priv; } return priv; } /** * genl_register_family - register a generic netlink family * @family: generic netlink family * * Registers the specified family after validating it first. Only one * family may be registered with the same family name or identifier. * * The family's ops, multicast groups and module pointer must already * be assigned. * * Return 0 on success or a negative error code. */ int genl_register_family(struct genl_family *family) { int err, i; int start = GENL_START_ALLOC, end = GENL_MAX_ID; err = genl_validate_ops(family); if (err) return err; genl_lock_all(); if (genl_family_find_byname(family->name)) { err = -EEXIST; goto errout_locked; } err = genl_sk_privs_alloc(family); if (err) goto errout_locked; /* * Sadly, a few cases need to be special-cased * due to them having previously abused the API * and having used their family ID also as their * multicast group ID, so we use reserved IDs * for both to be sure we can do that mapping. */ if (family == &genl_ctrl) { /* and this needs to be special for initial family lookups */ start = end = GENL_ID_CTRL; } else if (strcmp(family->name, "pmcraid") == 0) { start = end = GENL_ID_PMCRAID; } else if (strcmp(family->name, "VFS_DQUOT") == 0) { start = end = GENL_ID_VFS_DQUOT; } family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; goto errout_sk_privs_free; } err = genl_validate_assign_mc_groups(family); if (err) goto errout_remove; genl_unlock_all(); /* send all events */ genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL, 0); for (i = 0; i < family->n_mcgrps; i++) genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family, &family->mcgrps[i], family->mcgrp_offset + i); return 0; errout_remove: idr_remove(&genl_fam_idr, family->id); errout_sk_privs_free: genl_sk_privs_free(family); errout_locked: genl_unlock_all(); return err; } EXPORT_SYMBOL(genl_register_family); /** * genl_unregister_family - unregister generic netlink family * @family: generic netlink family * * Unregisters the specified family. * * Returns 0 on success or a negative error code. */ int genl_unregister_family(const struct genl_family *family) { genl_lock_all(); if (!genl_family_find_byid(family->id)) { genl_unlock_all(); return -ENOENT; } genl_unregister_mc_groups(family); idr_remove(&genl_fam_idr, family->id); up_write(&cb_lock); wait_event(genl_sk_destructing_waitq, atomic_read(&genl_sk_destructing_cnt) == 0); genl_sk_privs_free(family); genl_unlock(); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; } EXPORT_SYMBOL(genl_unregister_family); /** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message * @portid: netlink portid the message is addressed to * @seq: sequence number (usually the one of the sender) * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd) { struct nlmsghdr *nlh; struct genlmsghdr *hdr; nlh = nlmsg_put(skb, portid, seq, family->id, GENL_HDRLEN + family->hdrsize, flags); if (nlh == NULL) return NULL; hdr = nlmsg_data(nlh); hdr->cmd = cmd; hdr->version = family->version; hdr->reserved = 0; return (char *) hdr + GENL_HDRLEN; } EXPORT_SYMBOL(genlmsg_put); static struct genl_dumpit_info *genl_dumpit_info_alloc(void) { return kmalloc(sizeof(struct genl_dumpit_info), GFP_KERNEL); } static void genl_dumpit_info_free(const struct genl_dumpit_info *info) { kfree(info); } static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_split_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { enum netlink_validation validate = ops->validate & no_strict_flag ? NL_VALIDATE_LIBERAL : NL_VALIDATE_STRICT; struct nlattr **attrbuf; int err; if (!ops->maxattr) return NULL; attrbuf = kmalloc_array(ops->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy, validate, extack); if (err) { kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { kfree(attrbuf); } struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; const struct genl_split_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; const struct genl_split_ops *ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; ops = ctx->ops; if (!(ops->validate & GENL_DONT_VALIDATE_DUMP) && ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) return -EINVAL; attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, ops, ctx->hdrlen, GENL_DONT_VALIDATE_DUMP_STRICT); if (IS_ERR(attrs)) return PTR_ERR(attrs); info = genl_dumpit_info_alloc(); if (!info) { genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->op = *ops; info->info.family = ctx->family; info->info.snd_seq = cb->nlh->nlmsg_seq; info->info.snd_portid = NETLINK_CB(cb->skb).portid; info->info.nlhdr = cb->nlh; info->info.genlhdr = nlmsg_data(cb->nlh); info->info.attrs = attrs; genl_info_net_set(&info->info, sock_net(cb->skb->sk)); info->info.extack = cb->extack; memset(&info->info.ctx, 0, sizeof(info->info.ctx)); cb->data = info; if (ops->start) { genl_op_lock(ctx->family); rc = ops->start(cb); genl_op_unlock(ctx->family); } if (rc) { genl_family_rcv_msg_attrs_free(info->info.attrs); genl_dumpit_info_free(info); cb->data = NULL; } return rc; } static int genl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct genl_dumpit_info *dump_info = cb->data; const struct genl_split_ops *ops = &dump_info->op; struct genl_info *info = &dump_info->info; int rc; info->extack = cb->extack; genl_op_lock(info->family); rc = ops->dumpit(skb, cb); genl_op_unlock(info->family); return rc; } static int genl_done(struct netlink_callback *cb) { struct genl_dumpit_info *dump_info = cb->data; const struct genl_split_ops *ops = &dump_info->op; struct genl_info *info = &dump_info->info; int rc = 0; info->extack = cb->extack; if (ops->done) { genl_op_lock(info->family); rc = ops->done(cb); genl_op_unlock(info->family); } genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(dump_info); return rc; } static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; struct netlink_dump_control c = { .module = family->module, .data = &ctx, .start = genl_start, .dump = genl_dumpit, .done = genl_done, .extack = extack, }; int err; ctx.family = family; ctx.nlh = nlh; ctx.extack = extack; ctx.ops = ops; ctx.hdrlen = hdrlen; genl_op_unlock(family); err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); genl_op_lock(family); return err; } static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; struct genl_info info; int err; attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, GENL_DONT_VALIDATE_STRICT); if (IS_ERR(attrbuf)) return PTR_ERR(attrbuf); info.snd_seq = nlh->nlmsg_seq; info.snd_portid = NETLINK_CB(skb).portid; info.family = family; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); info.attrs = attrbuf; info.extack = extack; genl_info_net_set(&info, net); memset(&info.ctx, 0, sizeof(info.ctx)); if (ops->pre_doit) { err = ops->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); if (ops->post_doit) ops->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); return err; } static int genl_header_check(const struct genl_family *family, struct nlmsghdr *nlh, struct genlmsghdr *hdr, struct netlink_ext_ack *extack) { u16 flags; /* Only for commands added after we started validating */ if (hdr->cmd < family->resv_start_op) return 0; if (hdr->reserved) { NL_SET_ERR_MSG(extack, "genlmsghdr.reserved field is not 0"); return -EINVAL; } /* Old netlink flags have pretty loose semantics, allow only the flags * consumed by the core where we can enforce the meaning. */ flags = nlh->nlmsg_flags; if ((flags & NLM_F_DUMP) == NLM_F_DUMP) /* DUMP is 2 bits */ flags &= ~NLM_F_DUMP; if (flags & ~(NLM_F_REQUEST | NLM_F_ACK | NLM_F_ECHO)) { NL_SET_ERR_MSG(extack, "ambiguous or reserved bits set in nlmsg_flags"); return -EINVAL; } return 0; } static int genl_family_rcv_msg(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); struct genl_split_ops op; int hdrlen; u8 flags; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) return -ENOENT; hdrlen = GENL_HDRLEN + family->hdrsize; if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; if (genl_header_check(family, nlh, hdr, extack)) return -EINVAL; flags = (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP ? GENL_CMD_CAP_DUMP : GENL_CMD_CAP_DO; if (genl_get_cmd(hdr->cmd, flags, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((op.flags & GENL_UNS_ADMIN_PERM) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (flags & GENL_CMD_CAP_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else return genl_family_rcv_msg_doit(family, skb, nlh, extack, &op, hdrlen, net); } static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { const struct genl_family *family; int err; family = genl_family_find_byid(nlh->nlmsg_type); if (family == NULL) return -ENOENT; genl_op_lock(family); err = genl_family_rcv_msg(family, skb, nlh, extack); genl_op_unlock(family); return err; } static void genl_rcv(struct sk_buff *skb) { down_read(&cb_lock); netlink_rcv_skb(skb, &genl_rcv_msg); up_read(&cb_lock); } /************************************************************************** * Controller **************************************************************************/ static struct genl_family genl_ctrl; static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { struct genl_op_iter i; void *hdr; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -EMSGSIZE; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || nla_put_u32(skb, CTRL_ATTR_VERSION, family->version) || nla_put_u32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize) || nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; if (genl_op_iter_init(family, &i)) { struct nlattr *nla_ops; nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; while (genl_op_iter_next(&i)) { struct nlattr *nest; u32 op_flags; op_flags = i.flags; if (i.doit.policy || i.dumpit.policy) op_flags |= GENL_CMD_CAP_HASPOL; nest = nla_nest_start_noflag(skb, genl_op_iter_idx(&i)); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_OP_ID, i.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_ops); } if (family->n_mcgrps) { struct nlattr *nla_grps; int i; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; for (i = 0; i < family->n_mcgrps; i++) { struct nlattr *nest; const struct genl_multicast_group *grp; grp = &family->mcgrps[i]; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, family->mcgrp_offset + i) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_grps); } genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; struct nlattr *nla_grps; struct nlattr *nest; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id)) goto nla_put_failure; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; nest = nla_nest_start_noflag(skb, 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp_id) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) { int n = 0; struct genl_family *rt; struct net *net = sock_net(skb->sk); int fams_to_skip = cb->args[0]; unsigned int id; int err = 0; idr_for_each_entry(&genl_fam_idr, rt, id) { if (!rt->netnsok && !net_eq(net, &init_net)) continue; if (n++ < fams_to_skip) continue; err = ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, CTRL_CMD_NEWFAMILY); if (err) { n--; break; } } cb->args[0] = n; return err; } static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_info(family, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static struct sk_buff * ctrl_build_mcgrp_msg(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static const struct nla_policy ctrl_policy_family[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; const struct genl_family *res = NULL; int err = -EINVAL; if (info->attrs[CTRL_ATTR_FAMILY_ID]) { u16 id = nla_get_u16(info->attrs[CTRL_ATTR_FAMILY_ID]); res = genl_family_find_byid(id); err = -ENOENT; } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { char *name; name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); up_read(&cb_lock); request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); down_read(&cb_lock); genl_lock(); res = genl_family_find_byname(name); } #endif err = -ENOENT; } if (res == NULL) return err; if (!res->netnsok && !net_eq(genl_info_net(info), &init_net)) { /* family doesn't exist here */ return -ENOENT; } msg = ctrl_build_family_msg(res, info->snd_portid, info->snd_seq, CTRL_CMD_NEWFAMILY); if (IS_ERR(msg)) return PTR_ERR(msg); return genlmsg_reply(msg, info); } static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id) { struct sk_buff *msg; /* genl is still initialising */ if (!init_net.genl_sock) return 0; switch (event) { case CTRL_CMD_NEWFAMILY: case CTRL_CMD_DELFAMILY: WARN_ON(grp); msg = ctrl_build_family_msg(family, 0, 0, event); break; case CTRL_CMD_NEWMCAST_GRP: case CTRL_CMD_DELMCAST_GRP: BUG_ON(!grp); msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event); break; default: return -EINVAL; } if (IS_ERR(msg)) return PTR_ERR(msg); if (!family->netnsok) genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0, 0, GFP_KERNEL); else genlmsg_multicast_allns(&genl_ctrl, msg, 0, 0); return 0; } struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; struct genl_op_iter *op_iter; u32 op; u16 fam_id; u8 dump_map:1, single_op:1; }; static const struct nla_policy ctrl_policy_policy[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, [CTRL_ATTR_OP] = { .type = NLA_U32 }, }; static int ctrl_dumppolicy_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->info.attrs; const struct genl_family *rt; struct genl_op_iter i; int err; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) return -EINVAL; if (tb[CTRL_ATTR_FAMILY_ID]) { ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); } else { rt = genl_family_find_byname( nla_data(tb[CTRL_ATTR_FAMILY_NAME])); if (!rt) return -ENOENT; ctx->fam_id = rt->id; } rt = genl_family_find_byid(ctx->fam_id); if (!rt) return -ENOENT; ctx->rt = rt; if (tb[CTRL_ATTR_OP]) { struct genl_split_ops doit, dump; ctx->single_op = true; ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); err = genl_get_cmd_both(ctx->op, rt, &doit, &dump); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); return err; } if (doit.policy) { err = netlink_policy_dump_add_policy(&ctx->state, doit.policy, doit.maxattr); if (err) goto err_free_state; } if (dump.policy) { err = netlink_policy_dump_add_policy(&ctx->state, dump.policy, dump.maxattr); if (err) goto err_free_state; } if (!ctx->state) return -ENODATA; ctx->dump_map = 1; return 0; } ctx->op_iter = kmalloc(sizeof(*ctx->op_iter), GFP_KERNEL); if (!ctx->op_iter) return -ENOMEM; genl_op_iter_init(rt, ctx->op_iter); ctx->dump_map = genl_op_iter_next(ctx->op_iter); for (genl_op_iter_init(rt, &i); genl_op_iter_next(&i); ) { if (i.doit.policy) { err = netlink_policy_dump_add_policy(&ctx->state, i.doit.policy, i.doit.maxattr); if (err) goto err_free_state; } if (i.dumpit.policy) { err = netlink_policy_dump_add_policy(&ctx->state, i.dumpit.policy, i.dumpit.maxattr); if (err) goto err_free_state; } } if (!ctx->state) { err = -ENODATA; goto err_free_op_iter; } return 0; err_free_state: netlink_policy_dump_free(ctx->state); err_free_op_iter: kfree(ctx->op_iter); return err; } static void *ctrl_dumppolicy_prep(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &genl_ctrl, NLM_F_MULTI, CTRL_CMD_GETPOLICY); if (!hdr) return NULL; if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id)) return NULL; return hdr; } static int ctrl_dumppolicy_put_op(struct sk_buff *skb, struct netlink_callback *cb, struct genl_split_ops *doit, struct genl_split_ops *dumpit) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr *nest_pol, *nest_op; void *hdr; int idx; /* skip if we have nothing to show */ if (!doit->policy && !dumpit->policy) return 0; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) return -ENOBUFS; nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY); if (!nest_pol) goto err; nest_op = nla_nest_start(skb, doit->cmd); if (!nest_op) goto err; if (doit->policy) { idx = netlink_policy_dump_get_policy_idx(ctx->state, doit->policy, doit->maxattr); if (nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) goto err; } if (dumpit->policy) { idx = netlink_policy_dump_get_policy_idx(ctx->state, dumpit->policy, dumpit->maxattr); if (nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) goto err; } nla_nest_end(skb, nest_op); nla_nest_end(skb, nest_pol); genlmsg_end(skb, hdr); return 0; err: genlmsg_cancel(skb, hdr); return -ENOBUFS; } static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; if (ctx->dump_map) { if (ctx->single_op) { struct genl_split_ops doit, dumpit; if (WARN_ON(genl_get_cmd_both(ctx->op, ctx->rt, &doit, &dumpit))) return -ENOENT; if (ctrl_dumppolicy_put_op(skb, cb, &doit, &dumpit)) return skb->len; /* done with the per-op policy index list */ ctx->dump_map = 0; } while (ctx->dump_map) { if (ctrl_dumppolicy_put_op(skb, cb, &ctx->op_iter->doit, &ctx->op_iter->dumpit)) return skb->len; ctx->dump_map = genl_op_iter_next(ctx->op_iter); } } while (netlink_policy_dump_loop(ctx->state)) { struct nlattr *nest; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) goto nla_put_failure; nest = nla_nest_start(skb, CTRL_ATTR_POLICY); if (!nest) goto nla_put_failure; if (netlink_policy_dump_write(skb, ctx->state)) goto nla_put_failure; nla_nest_end(skb, nest); genlmsg_end(skb, hdr); } return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); return skb->len; } static int ctrl_dumppolicy_done(struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; kfree(ctx->op_iter); netlink_policy_dump_free(ctx->state); return 0; } static const struct genl_split_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, .validate = GENL_DONT_VALIDATE_STRICT, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, .flags = GENL_CMD_CAP_DO, }, { .cmd = CTRL_CMD_GETFAMILY, .validate = GENL_DONT_VALIDATE_DUMP, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .dumpit = ctrl_dumpfamily, .flags = GENL_CMD_CAP_DUMP, }, { .cmd = CTRL_CMD_GETPOLICY, .policy = ctrl_policy_policy, .maxattr = ARRAY_SIZE(ctrl_policy_policy) - 1, .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, .flags = GENL_CMD_CAP_DUMP, }, }; static const struct genl_multicast_group genl_ctrl_groups[] = { { .name = "notify", }, }; static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, .split_ops = genl_ctrl_ops, .n_split_ops = ARRAY_SIZE(genl_ctrl_ops), .resv_start_op = CTRL_CMD_GETPOLICY + 1, .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), .id = GENL_ID_CTRL, .name = "nlctrl", .version = 0x2, .netnsok = true, }; static int genl_bind(struct net *net, int group) { const struct genl_family *family; unsigned int id; int ret = 0; down_read(&cb_lock); idr_for_each_entry(&genl_fam_idr, family, id) { const struct genl_multicast_group *grp; int i; if (family->n_mcgrps == 0) continue; i = group - family->mcgrp_offset; if (i < 0 || i >= family->n_mcgrps) continue; grp = &family->mcgrps[i]; if ((grp->flags & GENL_MCAST_CAP_NET_ADMIN) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; if ((grp->flags & GENL_MCAST_CAP_SYS_ADMIN) && !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; if (family->bind) family->bind(i); break; } up_read(&cb_lock); return ret; } static void genl_unbind(struct net *net, int group) { const struct genl_family *family; unsigned int id; down_read(&cb_lock); idr_for_each_entry(&genl_fam_idr, family, id) { int i; if (family->n_mcgrps == 0) continue; i = group - family->mcgrp_offset; if (i < 0 || i >= family->n_mcgrps) continue; if (family->unbind) family->unbind(i); break; } up_read(&cb_lock); } static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, .bind = genl_bind, .unbind = genl_unbind, .release = genl_release, }; /* we'll bump the group number right afterwards */ net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); if (!net->genl_sock) return -ENOMEM; return 0; } static void __net_exit genl_pernet_exit(struct net *net) { netlink_kernel_release(net->genl_sock); net->genl_sock = NULL; } static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, }; static int __init genl_init(void) { int err; err = genl_register_family(&genl_ctrl); if (err < 0) goto problem; err = register_pernet_subsys(&genl_pernet_ops); if (err) goto problem; return 0; problem: panic("GENL: Cannot register controller: %d\n", err); } core_initcall(genl_init); static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group) { struct sk_buff *tmp; struct net *net, *prev = NULL; bool delivered = false; int err; rcu_read_lock(); for_each_net_rcu(net) { if (prev) { tmp = skb_clone(skb, GFP_ATOMIC); if (!tmp) { err = -ENOMEM; goto error; } err = nlmsg_multicast(prev->genl_sock, tmp, portid, group, GFP_ATOMIC); if (!err) delivered = true; else if (err != -ESRCH) goto error; } prev = net; } err = nlmsg_multicast(prev->genl_sock, skb, portid, group, GFP_ATOMIC); rcu_read_unlock(); if (!err) delivered = true; else if (err != -ESRCH) return err; return delivered ? 0 : -ESRCH; error: rcu_read_unlock(); kfree_skb(skb); return err; } int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group); } EXPORT_SYMBOL(genlmsg_multicast_allns); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags) { struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; group = family->mcgrp_offset + group; nlmsg_notify(sk, skb, info->snd_portid, group, nlmsg_report(info->nlhdr), flags); } EXPORT_SYMBOL(genl_notify); |
| 3 1 5 4 1 1 1 2 5 2 1 1 2 2 1 2 1 1 3 1 5 5 5 5 5 2 2 2 4 2 2 2 1 4 4 2 1 2 2 2 23 24 23 23 221 220 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_rwlock_t count; unsigned long last_gc; }; struct nft_rbtree_elem { struct nft_elem_priv priv; struct rb_node node; struct nft_set_ext ext; }; static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe) { return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) && (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END); } static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) { return !nft_rbtree_interval_end(rbe); } static int nft_rbtree_cmp(const struct nft_set *set, const struct nft_rbtree_elem *e1, const struct nft_rbtree_elem *e2) { return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), set->klen); } static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) { return nft_set_elem_expired(&rbe->ext); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) { struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; parent = rcu_dereference_raw(parent->rb_left); interval = NULL; continue; } *ext = &rbe->ext; return true; } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; } return false; } INDIRECT_CALLABLE_SCOPE bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); bool ret; ret = __nft_rbtree_lookup(net, set, key, ext, seq); if (ret || !read_seqcount_retry(&priv->count, seq)) return ret; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_lookup(net, set, key, ext, seq); read_unlock_bh(&priv->lock); return ret; } static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, const u32 *key, struct nft_rbtree_elem **elem, unsigned int seq, unsigned int flags, u8 genmask) { struct nft_rbtree_elem *rbe, *interval = NULL; struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent; const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); this = nft_set_ext_key(&rbe->ext); d = memcmp(this, key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (!(flags & NFT_SET_ELEM_INTERVAL_END)) interval = rbe; } else if (d > 0) { parent = rcu_dereference_raw(parent->rb_right); if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_set_elem_expired(&rbe->ext)) return false; if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { *elem = rbe; return true; } if (nft_rbtree_interval_end(rbe)) interval = NULL; parent = rcu_dereference_raw(parent->rb_left); } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && (flags & NFT_SET_ELEM_INTERVAL_END)))) { *elem = interval; return true; } return false; } static struct nft_elem_priv * nft_rbtree_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT); const u32 *key = (const u32 *)&elem->key.val; u8 genmask = nft_genmask_cur(net); bool ret; ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); if (ret || !read_seqcount_retry(&priv->count, seq)) return &rbe->priv; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); read_unlock_bh(&priv->lock); if (!ret) return ERR_PTR(-ENOENT); return &rbe->priv; } static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { lockdep_assert_held_write(&priv->lock); nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); } static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; struct nft_trans_gc *gc; gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they * are coupled with the interval start element. */ while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); } rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); /* There is always room in this trans gc for this element, * memory allocation never actually happens, hence, the warning * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, * this is synchronous gc which never fails. */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } nft_rbtree_gc_elem_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, struct nft_rbtree_elem *rbe, struct rb_node *first) { struct nft_rbtree_elem *first_elem; first_elem = rb_entry(first, struct nft_rbtree_elem, node); /* this element is closest to where the new element is to be inserted: * update the first element for the node list path. */ if (nft_rbtree_cmp(set, rbe, first_elem) < 0) return true; return false; } static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the * first element to walk the ordered elements to find possible overlap. */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) { p = &parent->rb_left; } else if (d > 0) { if (!first || nft_rbtree_update_first(set, rbe, first)) first = &rbe->node; p = &parent->rb_right; } else { if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } } if (!first) first = rb_first(&priv->root); /* Detect overlap by going through the list of valid tree nodes. * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ for (node = first; node != NULL; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) continue; /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); if (removed_end == rbe_le || removed_end == rbe_ge) return -EAGAIN; continue; } d = nft_rbtree_cmp(set, rbe, new); if (d == 0) { /* Matching end element: no need to look for an * overlapping greater or equal element. */ if (nft_rbtree_interval_end(rbe)) { rbe_le = rbe; break; } /* first element that is greater or equal to key value. */ if (!rbe_ge) { rbe_ge = rbe; continue; } /* this is a closer more or equal element, update it. */ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { rbe_ge = rbe; continue; } /* element is equal to key value, make sure flags are * the same, an existing more or equal start element * must not be replaced by more or equal end element. */ if ((nft_rbtree_interval_start(new) && nft_rbtree_interval_start(rbe_ge)) || (nft_rbtree_interval_end(new) && nft_rbtree_interval_end(rbe_ge))) { rbe_ge = rbe; continue; } } else if (d > 0) { /* annotate element greater than the new element. */ rbe_ge = rbe; continue; } else if (d < 0) { /* annotate element less than the new element. */ rbe_le = rbe; break; } } /* - new start element matching existing start element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { *elem_priv = &rbe_ge->priv; return -EEXIST; } /* - new end element matching existing end element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { *elem_priv = &rbe_le->priv; return -EEXIST; } /* - new start element with existing closest, less or equal key value * being a start element: partial overlap, reported as -ENOTEMPTY. * Anonymous sets allow for two consecutive start element since they * are constant, skip them to avoid bogus overlap reports. */ if (!nft_set_is_anonymous(set) && rbe_le && nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) return -ENOTEMPTY; /* - new end element with existing closest, less or equal key value * being a end element: partial overlap, reported as -ENOTEMPTY. */ if (rbe_le && nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* - new end element with existing closest, greater or equal key value * being an end element: partial overlap, reported as -ENOTEMPTY */ if (rbe_ge && nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* Accepted element: pick insertion point depending on key value */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; else if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; } static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); struct nft_rbtree *priv = nft_set_priv(set); int err; do { if (fatal_signal_pending(current)) return -EINTR; cond_resched(); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); err = __nft_rbtree_insert(net, set, rbe, elem_priv); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } while (err == -EAGAIN); return err; } static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } static void nft_rbtree_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); struct nft_rbtree *priv = nft_set_priv(set); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); } static struct nft_elem_priv * nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val, set->klen); if (d < 0) parent = parent->rb_left; else if (d > 0) parent = parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(this)) { parent = parent->rb_left; continue; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; } nft_rbtree_flush(net, set, &rbe->priv); return &rbe->priv; } } return NULL; } static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); if (iter->count < iter->skip) goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { read_unlock_bh(&priv->lock); return; } cont: iter->count++; } read_unlock_bh(&priv->lock); } static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { nft_setelem_data_deactivate(net, set, &rbe->priv); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_gc(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct net *net = read_pnet(&set->net); u64 tstamp = nft_net_tstamp(net); struct rb_node *node, *next; struct nft_trans_gc *gc; set = nft_set_container_of(priv); net = read_pnet(&set->net); gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) return; for (node = rb_first(&priv->root); node ; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is * always visited before the start element. */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!__nft_set_elem_expired(&rbe->ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; /* end element needs to be removed first, it has * no timeout extension. */ if (rbe_end) { nft_rbtree_gc_remove(net, set, priv, rbe_end); nft_trans_gc_elem_add(gc, rbe_end); rbe_end = NULL; } gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; nft_rbtree_gc_remove(net, set, priv, rbe); nft_trans_gc_elem_add(gc, rbe); } try_later: if (gc) { gc = nft_trans_gc_catchall_sync(gc); nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; } } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } static int nft_rbtree_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]) { struct nft_rbtree *priv = nft_set_priv(set); BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); rwlock_init(&priv->lock); seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; return 0; } static void nft_rbtree_destroy(const struct nft_ctx *ctx, const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } } static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { if (desc->field_count > 1) return false; if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * sizeof(struct nft_rbtree_elem); else est->size = ~0; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; return true; } static void nft_rbtree_commit(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) nft_rbtree_gc(set); } static void nft_rbtree_gc_init(const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); priv->last_gc = jiffies; } /* rbtree stores ranges as singleton elements, each range is composed of two * elements ... */ static u32 nft_rbtree_ksize(u32 size) { return size * 2; } /* ... hide this detail to userspace. */ static u32 nft_rbtree_usize(u32 size) { if (!size) return 0; return size / 2; } static u32 nft_rbtree_adjust_maxsize(const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; const void *key; node = rb_last(&priv->root); if (!node) return 0; rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_rbtree_interval_end(rbe)) return 0; key = nft_set_ext_key(&rbe->ext); if (memchr(key, 1, set->klen)) return 0; /* this is the all-zero no-match element. */ return 1; } const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, .deactivate = nft_rbtree_deactivate, .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, .commit = nft_rbtree_commit, .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, .ksize = nft_rbtree_ksize, .usize = nft_rbtree_usize, .adjust_maxsize = nft_rbtree_adjust_maxsize, }, }; |
| 4 4 1 4 4 4 4 1 3 190 8 2 178 177 1 2 179 40 22 3 167 156 14 168 164 4 4 1 22 6 140 2 163 3 3 3 3 3 9 256 257 243 244 33 33 3 30 10 19 29 29 1 25 25 5 5 16 4 4 3 1 2 21 21 21 21 21 5 5 5 5 15 21 21 25 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 4 4 4 4 4 4 4 4 6 14 2 43 43 14 29 5 23 5 19 15 30 30 3 25 3 3 9 12 12 20 1 20 20 20 20 20 17 5 8 4 5 1 4 20 1 19 1 7 14 3 3 6 2 6 3 3 3 3 3 7 7 7 7 6 6 5 1 13 8 5 205 110 110 111 45 72 72 130 13 13 117 130 5 86 86 5 82 80 2 78 66 16 10 10 1 72 52 51 59 59 59 59 2 57 1 56 55 54 43 24 1 5 5 4 4 1 1 24 1 2 13 10 10 12 11 2 28 39 2 4 61 62 62 151 108 108 108 109 109 104 5 93 31 108 146 229 232 146 146 146 146 146 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * IPv4 specific functions * * code split from: * linux/ipv4/tcp.c * linux/ipv4/tcp_input.c * linux/ipv4/tcp_output.c * * See tcp.c for author information */ /* * Changes: * David S. Miller : New socket lookup architecture. * This code is dedicated to John Dyson. * David S. Miller : Change semantics of established hash, * half is devoted to TIME_WAIT sockets * and the rest go in the other half. * Andi Kleen : Add support for syncookies and fixed * some bugs: ip options weren't passed to * the TCP layer, missed a check for an * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen semantics. * Mike McLagan : Routing by source * Juan Jose Ciarlante: ip_dynaddr bits * Andi Kleen: various fixes. * Vitaly E. Lavrov : Transparent proxy revived after year * coma. * Andi Kleen : Fix new listen. * Andi Kleen : Fix accept error reporting. * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/random.h> #include <linux/cache.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/sched.h> #include <net/aligned_data.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/tcp.h> #include <net/transp_v6.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <linux/inet.h> #include <linux/ipv6.h> #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> #include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; static DEFINE_MUTEX(tcp_exit_batch_mutex); static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; u32 reuse_thresh; if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) reuse = 0; if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address * or direct binding to 'lo' interface. */ bool loopback = false; if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) loopback = true; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { if (ipv6_addr_loopback(&tw->tw_v6_daddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) || ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr)) loopback = true; } else #endif { if (ipv4_is_loopback(tw->tw_daddr) || ipv4_is_loopback(tw->tw_rcv_saddr)) loopback = true; } if (!loopback) reuse = 0; } /* With PAWS, it is safe from the viewpoint of data integrity. Even without PAWS it is safe provided sequence spaces do not overlap i.e. at data rates <= 80Mbit/sec. Actually, the idea is close to VJ's one, only timestamp cache is held not per host, but per port pair and TW bucket is used as state holder. If TW bucket has been already destroyed we fall back to VJ's scheme and use initial timestamp retrieved from peer table. */ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); reuse_thresh = READ_ONCE(tw->tw_entry_stamp) + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse_delay); if (ts_recent_stamp && (!twp || (reuse && time_after32(tcp_clock_ms(), reuse_thresh)))) { /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) return 0; /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair * process. * * Without this check re-using a TIME-WAIT socket with TCP * repair would accumulate a -1 on the repair assigned * sequence number. The first time it is reused the sequence * is -1, the second time -2, etc. This fixes that issue * without appearing to create any others. */ if (likely(!tp->repair)) { u32 seq = tcptw->tw_snd_nxt + 65535 + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent); tp->rx_opt.ts_recent_stamp = ts_recent_stamp; } return 1; } return 0; } EXPORT_IPV6_MOD_GPL(tcp_twsk_unique); static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len); } /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return err; } if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } if (!inet_opt || !inet_opt->opt.srr) daddr = fl4->daddr; tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } } else { sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket * lock select source port, enter ourselves into the hash tables and * complete initialization after this. */ tcp_set_state(sk, TCP_SYN_SENT); err = inet_hash_connect(tcp_death_row, sk); if (err) goto failure; sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst); /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); rt = NULL; if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcp_seq(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, usin->sin_port)); WRITE_ONCE(tp->tsoffset, secure_tcp_ts_off(net, inet->inet_saddr, inet->inet_daddr)); } atomic_set(&inet->inet_id, get_random_u16()); if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto failure; err = tcp_connect(sk); if (err) goto failure; return 0; failure: /* * This unhashes the socket and releases the local port, * if necessary. */ tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; return err; } EXPORT_IPV6_MOD(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ void tcp_v4_mtu_reduced(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) WRITE_ONCE(sk->sk_err_soft, EMSGSIZE); mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { tcp_sync_mss(sk, mtu); /* Resend the TCP packet because it's * clear that the old packet has been * dropped. This is the new "fast" path mtu * discovery. */ tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } EXPORT_IPV6_MOD(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) dst->ops->redirect(dst, sk, skb); } /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ if (seq != tcp_rsk(req)->snt_isn) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); tcp_listendrop(req->rsk_listener); } reqsk_put(req); } EXPORT_IPV6_MOD(tcp_req_err); /* TCP-LD (RFC 6069) logic */ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; s32 remaining; u32 delta_us; if (sock_owned_by_user(sk)) return; if (seq != tp->snd_una || !icsk->icsk_retransmits || !icsk->icsk_backoff) return; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) return; icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, tcp_rto_max(sk)); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); if (remaining > 0) { tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, false); } else { /* RTO revert clocked out retransmission. * Will retransmit now. */ tcp_retransmit_timer(sk); } } EXPORT_IPV6_MOD(tcp_ld_RTO_revert); /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the tcp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */ int tcp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct net *net = dev_net_rcu(skb->dev); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct request_sock *fastopen; struct tcp_sock *tp; u32 seq, snd_una; struct sock *sk; int err; sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB || type == ICMP_TIME_EXCEEDED || (type == ICMP_DEST_UNREACH && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH))); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ if (sock_owned_by_user(sk)) { if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); } if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } goto out; } err = icmp_err_convert[code].errno; /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH)) tcp_ld_RTO_revert(sk, seq); break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { /* Only an error on timeout */ WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } EXPORT_IPV6_MOD(tcp_v4_send_check); #define REPLY_OPTIONS_LEN (MAX_TCP_OPTION_SPACE / sizeof(__be32)) static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, const struct tcp_ao_hdr *aoh, struct ip_reply_arg *arg, struct tcphdr *reply, __be32 reply_options[REPLY_OPTIONS_LEN]) { #ifdef CONFIG_TCP_AO int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); int l3index = sdif ? dif : 0; bool allocated_traffic_key; struct tcp_ao_key *key; char *traffic_key; bool drop = true; u32 ao_sne = 0; u8 keyid; rcu_read_lock(); if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, ntohl(reply->seq), &key, &traffic_key, &allocated_traffic_key, &keyid, &ao_sne)) goto out; reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | (aoh->rnext_keyid << 8) | keyid); arg->iov[0].iov_len += tcp_ao_len_aligned(key); reply->doff = arg->iov[0].iov_len / 4; if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], key, traffic_key, (union tcp_ao_addr *)&ip_hdr(skb)->saddr, (union tcp_ao_addr *)&ip_hdr(skb)->daddr, reply, ao_sne)) goto out; drop = false; out: rcu_read_unlock(); if (allocated_traffic_key) kfree(traffic_key); return drop; #else return true; #endif } /* * This routine will send an RST to the other tcp. * * Someone asks: why I NEVER use socket parameters (TOS, TTL etc.) * for reset. * Answer: if a packet caused RST, it is not for a socket * existing in our system, if it is matched to a socket, * it is just duplicate segment or bug in other side's TCP. * So that we build reply only basing on parameters * arrived with segment. * Exception: precedence violation. We do not implement it in any case. */ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[REPLY_OPTIONS_LEN]; } rep; const __u8 *md5_hash_location = NULL; const struct tcp_ao_hdr *aoh; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key = NULL; unsigned char newhash[16]; struct sock *sk1 = NULL; int genhash; #endif u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; u32 txhash = 0; /* Never send a reset in response to a reset. */ if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ memset(&rep, 0, sizeof(rep)); rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = sizeof(struct tcphdr) / 4; rep.th.rst = 1; if (th->ack) { rep.th.seq = th->ack_seq; } else { rep.th.ack = 1; rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2)); } memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh)) return; if (aoh && tcp_v4_ao_sign_reset(sk, skb, aoh, &arg, &rep.th, rep.opt)) return; #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); if (sk && sk_fullsock(sk)) { const union tcp_md5_addr *addr; int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } else if (md5_hash_location) { const union tcp_md5_addr *addr; int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = sdif ? dif : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); if (!key) goto out; genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) goto out; } if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* Update length and the length the header thinks exists */ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len / 4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif /* Can't co-exist with TCPMD5, hence check rep.opt[0] */ if (rep.opt[0] == 0) { __be32 mrst = mptcp_reset_option(skb); if (mrst) { rep.opt[0] = mrst; arg.iov[0].iov_len += sizeof(mrst); rep.th.doff = arg.iov[0].iov_len / 4; } } arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; trace_tcp_send_reset(sk, skb, reason); BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); /* ECN bits of TW reset are cleared */ arg.tos = ip_hdr(skb)->tos & ~INET_ECN_MASK; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); txhash = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_txhash : sk->sk_txhash; } else { ctl_sk->sk_mark = 0; ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time, txhash); xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG out: rcu_read_unlock(); #endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states outside socket context is ugly, certainly. What can I do? */ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_key *key, int reply_flags, u8 tos, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(MAX_TCP_OPTION_SPACE >> 2)]; } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; struct sock *ctl_sk; u64 transmit_time; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tsval); rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } /* Swap the send and the receive. */ rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = arg.iov[0].iov_len / 4; rep.th.seq = htonl(seq); rep.th.ack_seq = htonl(ack); rep.th.ack = 1; rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG if (tcp_key_is_md5(key)) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], key->md5_key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif #ifdef CONFIG_TCP_AO if (tcp_key_is_ao(key)) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | key->rcv_next); arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], key->ao_key, key->traffic_key, (union tcp_ao_addr *)&ip_hdr(skb)->saddr, (union tcp_ao_addr *)&ip_hdr(skb)->daddr, &rep.th, key->sne); } #endif arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; if (oif) arg.bound_dev_if = oif; arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time, txhash); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb, enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); struct tcp_key key = {}; u8 tos = tw->tw_tos; /* Cleaning only ECN bits of TW ACKs of oow data or is paws_reject, * while not cleaning ECN bits of other TW ACKs to avoid these ACKs * being placed in a different service queues (Classic rather than L4S) */ if (tw_status == TCP_TW_ACK_OOW) tos &= ~INET_ECN_MASK; #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; if (static_branch_unlikely(&tcp_ao_needed.key)) { /* FIXME: the segment to-be-acked is not verified yet */ ao_info = rcu_dereference(tcptw->ao_info); if (ao_info) { const struct tcp_ao_hdr *aoh; if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) { inet_twsk_put(tw); return; } if (aoh) key.ao_key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); } } if (key.ao_key) { struct tcp_ao_key *rnext_key; key.traffic_key = snd_other_key(key.ao_key); key.sne = READ_ONCE(ao_info->snd_sne); rnext_key = READ_ONCE(ao_info->rnext_key); key.rcv_next = rnext_key->rcvid; key.type = TCP_KEY_AO; #else if (0) { #endif } else if (static_branch_tcp_md5()) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; } tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tos, tw->tw_txhash); inet_twsk_put(tw); } static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_key key = {}; /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key) && tcp_rsk_used_ao(req)) { const union tcp_md5_addr *addr; const struct tcp_ao_hdr *aoh; int l3index; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) return; if (!aoh) return; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, aoh->rnext_keyid, -1); if (unlikely(!key.ao_key)) { /* Send ACK with any matching MKT for the peer */ key.ao_key = tcp_ao_do_lookup(sk, l3index, addr, AF_INET, -1, -1); /* Matching key disappeared (user removed the key?) * let the handshake timeout. */ if (!key.ao_key) { net_info_ratelimited("TCP-AO key for (%pI4, %d)->(%pI4, %d) suddenly disappeared, won't ACK new connection\n", addr, ntohs(tcp_hdr(skb)->source), &ip_hdr(skb)->daddr, ntohs(tcp_hdr(skb)->dest)); return; } } key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); if (!key.traffic_key) return; key.type = TCP_KEY_AO; key.rcv_next = aoh->keyid; tcp_v4_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); #else if (0) { #endif } else if (static_branch_tcp_md5()) { const union tcp_md5_addr *addr; int l3index; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key.md5_key) key.type = TCP_KEY_MD5; } /* Cleaning ECN bits of TW ACKs of oow data or is paws_reject */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), req->ts_recent, 0, &key, inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos & ~INET_ECN_MASK, READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); } /* * Send a SYN-ACK after having received a SYN. * This still operates on a request_sock only, not on a big * socket. */ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = READ_ONCE(inet_sk(sk)->tos); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) tos = (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (tos & INET_ECN_MASK); if (!INET_ECN_is_capable(tos) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tos |= INET_ECN_ECT_0; rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), tos); rcu_read_unlock(); err = net_xmit_eval(err); } return err; } /* * IPv4 request_sock destructor. */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG /* * RFC2385 MD5 checksumming requires a mapping of * IP address->MD5 Key. * We need to maintain these in the sk structure. */ DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); EXPORT_IPV6_MOD(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) { if (!old) return true; /* l3index always overrides non-l3index */ if (old->l3index && new->l3index == 0) return false; if (old->l3index == 0 && new->l3index) return true; return old->prefixlen < new->prefixlen; } /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; const struct tcp_md5sig_info *md5sig; __be32 mask; struct tcp_md5sig_key *best_match = NULL; bool match; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (!any_l3index && key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == (addr->a4.s_addr & mask); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, key->prefixlen); #endif } else { match = false; } if (match && better_md5_match(best_match, key)) best_match = key; } return best_match; } EXPORT_IPV6_MOD(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) size = sizeof(struct in6_addr); #endif hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if ((key->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX)) continue; if (key->l3index != l3index) continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; } return NULL; } struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } EXPORT_IPV6_MOD(tcp_v4_md5_lookup); static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) return -ENOMEM; sk_gso_disable(sk); INIT_HLIST_HEAD(&md5sig->head); rcu_assign_pointer(tp->md5sig_info, md5sig); return 0; } /* This can be called on a newly created socket, from other files */ static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (key) { /* Pre-existing entry - just update that one. * Note that the key might be used concurrently. * data_race() is telling kcsan that we do not care of * key mismatches, since changing MD5 key on live flows * can lead to packet drops. */ data_race(memcpy(key->key, newkey, newkeylen)); /* Pairs with READ_ONCE() in tcp_md5_hash_key(). * Also note that a reader could catch new key->keylen value * but old key->key[], this is the reason we use __GFP_ZERO * at sock_kmalloc() time below these lines. */ WRITE_ONCE(key->keylen, newkeylen); return 0; } md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; key->l3index = l3index; key->flags = flags; memcpy(&key->addr, addr, (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen) { struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { if (tcp_md5_alloc_sigpool()) return -ENOMEM; if (tcp_md5sig_info_add(sk, GFP_KERNEL)) { tcp_md5_release_sigpool(); return -ENOMEM; } if (!static_branch_inc(&tcp_md5_needed.key)) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); tcp_md5_release_sigpool(); return -EUSERS; } } return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, newkey, newkeylen, GFP_KERNEL); } EXPORT_IPV6_MOD(tcp_md5_do_add); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, struct tcp_md5sig_key *key) { struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { tcp_md5_add_sigpool(); if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) { tcp_md5_release_sigpool(); return -ENOMEM; } if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); tcp_md5_release_sigpool(); return -EUSERS; } } return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } EXPORT_IPV6_MOD(tcp_md5_key_copy); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { struct tcp_md5sig_key *key; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (!key) return -ENOENT; hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); return 0; } EXPORT_IPV6_MOD(tcp_md5_do_del); void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); } } static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; const union tcp_md5_addr *addr; u8 prefixlen = 32; int l3index = 0; bool l3flag; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin->sin_family != AF_INET) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 32) return -EINVAL; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index, flags); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v4_md5_hash_headers(struct tcp_sigpool *hp, __be32 daddr, __be32 saddr, const struct tcphdr *th, int nbytes) { struct tcp4_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; bp->saddr = saddr; bp->daddr = daddr; bp->pad = 0; bp->protocol = IPPROTO_TCP; bp->len = cpu_to_be16(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->req); } static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_sigpool hp; if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct tcp_sigpool hp; __be32 saddr, daddr; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; } if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb); #endif static void tcp_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { tcp_v4_init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v4_ao_lookup_rsk, .ao_calc_key = tcp_v4_ao_calc_key_rsk, .ao_synack_hash = tcp_v4_ao_synack_hash, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, .init_seq = tcp_v4_init_seq, .init_ts_off = tcp_v4_init_ts_off, .send_synack = tcp_v4_send_synack, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; return tcp_conn_request(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, skb); drop: tcp_listendrop(sk); return 0; } EXPORT_IPV6_MOD(tcp_v4_conn_request); /* * The three way handshake has completed - we got a valid synack - * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG const union tcp_md5_addr *addr; struct tcp_md5sig_key *key; int l3index; #endif struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; atomic_set(&newinet->inet_id, get_random_u16()); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) goto put_and_exit; } else { /* syncookie case : see end of cookie_v4_check() */ } sk_setup_caps(newsk, dst); tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key && !tcp_rsk_used_ao(req)) { if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key)) goto put_and_exit; sk_gso_disable(newsk); } #endif #ifdef CONFIG_TCP_AO if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET)) goto put_and_exit; /* OOM, release back memory */ #endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { newinet->inet_opt = NULL; if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; exit_overflow: NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: tcp_listendrop(sk); return NULL; put_and_exit: newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; } EXPORT_IPV6_MOD(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v4_check(sk, skb); #endif return sk; } u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, th); if (mss) { *cookie = __cookie_v4_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || !INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check, dst, 0)) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) return 0; if (nsk != sk) { reason = tcp_child_process(sk, nsk, skb); if (reason) { rsk = nsk; goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); if (reason) { rsk = sk; goto reset; } return 0; reset: tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: sk_skb_reason_drop(sk, skb, reason); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, * but you have been warned. */ return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return 0; sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; struct sk_buff *tail; unsigned int hdrlen; bool fragstolen; u32 gso_segs; u32 gso_size; u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. * This is valid because skb is not yet charged to the socket. * It has been noticed pure SACK packets were sometimes dropped * (if cooked by drivers without copybreak feature). */ skb_condense(skb); tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); trace_tcp_bad_csum(skb); *reason = SKB_DROP_REASON_TCP_CSUM; __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; } /* Attempt coalescing to last skb in backlog, even if we are * above the limits. * This is okay because skb capacity is limited to MAX_SKB_FRAGS. */ th = (const struct tcphdr *)skb->data; hdrlen = th->doff * 4; tail = sk->sk_backlog.tail; if (!tail) goto no_coalesce; thtail = (struct tcphdr *)tail->data; if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || ((TCP_SKB_CB(tail)->tcp_flags | TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || !((TCP_SKB_CB(tail)->tcp_flags & TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)) || !tcp_skb_can_collapse_rx(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; __skb_pull(skb, hdrlen); shinfo = skb_shinfo(skb); gso_size = shinfo->gso_size ?: skb->len; gso_segs = shinfo->gso_segs ?: 1; shinfo = skb_shinfo(tail); tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen); tail_gso_segs = shinfo->gso_segs ?: 1; if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; thtail->window = th->window; } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() * is not entered if we append a packet with a FIN. * SYN, RST, URG are not present. * ACK is set on both packets. * PSH : we do not really care in TCP stack, * at least for 'GRO' packets. */ thtail->fin |= th->fin; TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; if (TCP_SKB_CB(skb)->has_rxtstamp) { TCP_SKB_CB(tail)->has_rxtstamp = true; tail->tstamp = skb->tstamp; skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp; } /* Not as strict as GRO. We only need to carry mss max value */ shinfo->gso_size = max(gso_size, tail_gso_size); shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF); sk->sk_backlog.len += delta; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGCOALESCE); kfree_skb_partial(skb, fragstolen); return false; } __skb_push(skb, hdrlen); no_coalesce: /* sk->sk_backlog.len is reset only at the end of __release_sock(). * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach * sk_rcvbuf in normal conditions. */ limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ limit += 64 * 1024; limit = min_t(u64, limit, UINT_MAX); if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); return true; } return false; } EXPORT_IPV6_MOD(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_IPV6_MOD(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, sizeof(struct inet_skb_parm)); } static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, const struct tcphdr *th) { /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() * barrier() makes sure compiler wont play fool^Waliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), sizeof(struct inet_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } /* * From tcp_input.c */ int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; enum tcp_tw_status tw_status; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk = NULL; bool refcounted; int ret; u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* Count it even if it's bad */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; /* An explanation is required here, I think. * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else drop_reason = tcp_inbound_hash(sk, req, skb, &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (unlikely(drop_reason)) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { /* We own a reference on the listener, increase it again * as we might lose it too soon. */ sock_hold(sk); } refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); } else { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v4_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { enum sk_rst_reason rst_reason; rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v4_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); return 0; } } process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_hash(sk, NULL, skb, &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (drop_reason) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v4_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v4_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v4_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); /* Discard frame. */ sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn, &drop_reason); switch (tw_status) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; __this_cpu_write(tcp_tw_isn, isn); goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: case TCP_TW_ACK_OOW: tcp_v4_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; } static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_destructor= tcp_twsk_destructor, }; void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; } } EXPORT_IPV6_MOD(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_IPV6_MOD(ipv4_specific); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v4_ao_lookup, .calc_ao_hash = tcp_v4_ao_hash_skb, .ao_parse = tcp_v4_parse_ao, .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif return 0; } #ifdef CONFIG_TCP_MD5SIG static void tcp_md5sig_info_free_rcu(struct rcu_head *head) { struct tcp_md5sig_info *md5sig; md5sig = container_of(head, struct tcp_md5sig_info, rcu); kfree(md5sig); static_branch_slow_dec_deferred(&tcp_md5_needed); tcp_md5_release_sigpool(); } #endif static void tcp_release_user_frags(struct sock *sk) { #ifdef CONFIG_PAGE_POOL unsigned long index; void *netmem; xa_for_each(&sk->sk_user_frags, index, netmem) WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); #endif } void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tcp_release_user_frags(sk); xa_destroy(&sk->sk_user_frags); trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); tcp_cleanup_congestion_control(sk); tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); /* Check if we want to disable active TFO */ tcp_fastopen_active_disable_ofo_check(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); tcp_clear_md5_list(sk); call_rcu(&md5sig->rcu, tcp_md5sig_info_free_rcu); rcu_assign_pointer(tp->md5sig_info, NULL); } #endif tcp_ao_destroy_sock(sk, false); /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); } EXPORT_IPV6_MOD(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ static unsigned short seq_file_family(const struct seq_file *seq); static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) { unsigned short family = seq_file_family(seq); /* AF_UNSPEC is used as a match all */ return ((family == AF_UNSPEC || family == sk->sk_family) && net_eq(sock_net(sk), seq_file_net(seq))); } /* Find a non empty bucket (starting from st->bucket) * and return the first sk from it. */ static void *listening_get_first(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; for (; st->bucket <= hinfo->lhash2_mask; st->bucket++) { struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; struct sock *sk; ilb2 = &hinfo->lhash2[st->bucket]; if (hlist_nulls_empty(&ilb2->nulls_head)) continue; spin_lock(&ilb2->lock); sk_nulls_for_each(sk, node, &ilb2->nulls_head) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock(&ilb2->lock); } return NULL; } /* Find the next sk of "cur" within the same bucket (i.e. st->bucket). * If "cur" is the last one in the st->bucket, * call listening_get_first() to return the first sk of the next * non empty bucket. */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct tcp_iter_state *st = seq->private; struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; struct inet_hashinfo *hinfo; struct sock *sk = cur; ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) return sk; } hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; ilb2 = &hinfo->lhash2[st->bucket]; spin_unlock(&ilb2->lock); ++st->bucket; return listening_get_first(seq); } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; st->offset = 0; rc = listening_get_first(seq); while (rc && *pos) { rc = listening_get_next(seq, rc); --*pos; } return rc; } static inline bool empty_bucket(struct inet_hashinfo *hinfo, const struct tcp_iter_state *st) { return hlist_nulls_empty(&hinfo->ehash[st->bucket].chain); } /* * Get first established socket starting from bucket given in st->bucket. * If st->bucket is zero, the very first socket in the hash is returned. */ static void *established_get_first(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; for (; st->bucket <= hinfo->ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; spinlock_t *lock = inet_ehash_lockp(hinfo, st->bucket); cond_resched(); /* Lockless fast path for the common case of empty buckets */ if (empty_bucket(hinfo, st)) continue; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &hinfo->ehash[st->bucket].chain) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock_bh(lock); } return NULL; } static void *established_get_next(struct seq_file *seq, void *cur) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; struct hlist_nulls_node *node; struct sock *sk = cur; ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) return sk; } spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); ++st->bucket; return established_get_first(seq); } static void *established_get_idx(struct seq_file *seq, loff_t pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); --pos; } return rc; } static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; struct tcp_iter_state *st = seq->private; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } return rc; } static void *tcp_seek_last_pos(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (st->bucket > hinfo->lhash2_mask) break; rc = listening_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; st->bucket = 0; st->state = TCP_SEQ_STATE_ESTABLISHED; fallthrough; case TCP_SEQ_STATE_ESTABLISHED: if (st->bucket > hinfo->ehash_mask) break; rc = established_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } st->num = orig_num; return rc; } void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; if (*pos && *pos == st->last_pos) { rc = tcp_seek_last_pos(seq); if (rc) goto out; } st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; st->bucket = 0; st->offset = 0; rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; out: st->last_pos = *pos; return rc; } EXPORT_IPV6_MOD(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc = NULL; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } switch (st->state) { case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; st->offset = 0; rc = established_get_first(seq); } break; case TCP_SEQ_STATE_ESTABLISHED: rc = established_get_next(seq, v); break; } out: ++*pos; st->last_pos = *pos; return rc; } EXPORT_IPV6_MOD(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) spin_unlock(&hinfo->lhash2[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); break; } } EXPORT_IPV6_MOD(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, ireq->ir_loc_addr, ireq->ir_num, ireq->ir_rmt_addr, ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->num_timeout, from_kuid_munged(seq_user_ns(f), sk_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) { int timer_active; unsigned long timer_expires; const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); u8 icsk_pending; int rx_queue; int state; icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk_timeout(icsk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk_timeout(icsk); } else if (timer_pending(&sk->sk_timer)) { timer_active = 2; timer_expires = sk->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sk); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sk->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(f), sk_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i) { long delta = tw->tw_timer.expires - jiffies; __be32 dest, src; __u16 destp, srcp; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 static int tcp4_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; seq_setwidth(seq, TMPSZ - 1); if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait4_sock(v, seq, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq4(v, seq, st->num); else get_tcp4_sock(v, seq, st->num); out: seq_pad(seq, '\n'); return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_tcp_iter_state { struct tcp_iter_state state; unsigned int cur_sk; unsigned int end_sk; unsigned int max_sk; struct sock **batch; bool st_bucket_done; }; struct bpf_iter__tcp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct sock_common *, sk_common); uid_t uid __aligned(8); }; static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) { struct bpf_iter__tcp ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk_common = sk_common; ctx.uid = uid; return bpf_iter_run_prog(prog, &ctx); } static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, unsigned int new_batch_sz) { struct sock **new_batch; new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, GFP_USER | __GFP_NOWARN); if (!new_batch) return -ENOMEM; bpf_iter_tcp_put_batch(iter); kvfree(iter->batch); iter->batch = new_batch; iter->max_sk = new_batch_sz; return 0; } static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, struct sock *start_sk) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; sock_hold(start_sk); iter->batch[iter->end_sk++] = start_sk; sk = sk_nulls_next(start_sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); iter->batch[iter->end_sk++] = sk; } expected++; } } spin_unlock(&hinfo->lhash2[st->bucket].lock); return expected; } static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, struct sock *start_sk) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; sock_hold(start_sk); iter->batch[iter->end_sk++] = start_sk; sk = sk_nulls_next(start_sk); sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); iter->batch[iter->end_sk++] = sk; } expected++; } } spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); return expected; } static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; unsigned int expected; bool resized = false; struct sock *sk; /* The st->bucket is done. Directly advance to the next * bucket instead of having the tcp_seek_last_pos() to skip * one by one in the current bucket and eventually find out * it has to advance to the next bucket. */ if (iter->st_bucket_done) { st->offset = 0; st->bucket++; if (st->state == TCP_SEQ_STATE_LISTENING && st->bucket > hinfo->lhash2_mask) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; } } again: /* Get a new batch */ iter->cur_sk = 0; iter->end_sk = 0; iter->st_bucket_done = false; sk = tcp_seek_last_pos(seq); if (!sk) return NULL; /* Done */ if (st->state == TCP_SEQ_STATE_LISTENING) expected = bpf_iter_tcp_listening_batch(seq, sk); else expected = bpf_iter_tcp_established_batch(seq, sk); if (iter->end_sk == expected) { iter->st_bucket_done = true; return sk; } if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) { resized = true; goto again; } return sk; } static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos) { /* bpf iter does not support lseek, so it always * continue from where it was stop()-ped. */ if (*pos) return bpf_iter_tcp_batch(seq); return SEQ_START_TOKEN; } static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct sock *sk; /* Whenever seq_next() is called, the iter->cur_sk is * done with seq_show(), so advance to the next sk in * the batch. */ if (iter->cur_sk < iter->end_sk) { /* Keeping st->num consistent in tcp_iter_state. * bpf_iter_tcp does not use st->num. * meta.seq_num is used instead. */ st->num++; /* Move st->offset to the next sk in the bucket such that * the future start() will resume at st->offset in * st->bucket. See tcp_seek_last_pos(). */ st->offset++; sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) sk = iter->batch[iter->cur_sk]; else sk = bpf_iter_tcp_batch(seq); ++*pos; /* Keeping st->last_pos consistent in tcp_iter_state. * bpf iter does not do lseek, so st->last_pos always equals to *pos. */ st->last_pos = *pos; return sk; } static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; int ret; if (v == SEQ_START_TOKEN) return 0; if (sk_fullsock(sk)) lock_sock(sk); if (unlikely(sk_unhashed(sk))) { ret = SEQ_SKIP; goto unlock; } if (sk->sk_state == TCP_TIME_WAIT) { uid = 0; } else if (sk->sk_state == TCP_NEW_SYN_RECV) { const struct request_sock *req = v; uid = from_kuid_munged(seq_user_ns(seq), sk_uid(req->rsk_listener)); } else { uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk)); } meta.seq = seq; prog = bpf_iter_get_info(&meta, false); ret = tcp_prog_seq_show(prog, &meta, v, uid); unlock: if (sk_fullsock(sk)) release_sock(sk); return ret; } static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) { struct bpf_tcp_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)tcp_prog_seq_show(prog, &meta, v, 0); } if (iter->cur_sk < iter->end_sk) { bpf_iter_tcp_put_batch(iter); iter->st_bucket_done = false; } } static const struct seq_operations bpf_iter_tcp_seq_ops = { .show = bpf_iter_tcp_seq_show, .start = bpf_iter_tcp_seq_start, .next = bpf_iter_tcp_seq_next, .stop = bpf_iter_tcp_seq_stop, }; #endif static unsigned short seq_file_family(const struct seq_file *seq) { const struct tcp_seq_afinfo *afinfo; #ifdef CONFIG_BPF_SYSCALL /* Iterated from bpf_iter. Let the bpf prog to filter instead. */ if (seq->op == &bpf_iter_tcp_seq_ops) return AF_UNSPEC; #endif /* Iterated from proc fs */ afinfo = pde_data(file_inode(seq->file)); return afinfo->family; } static const struct seq_operations tcp4_seq_ops = { .show = tcp4_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp4_seq_afinfo = { .family = AF_INET, }; static int __net_init tcp4_proc_init_net(struct net *net) { if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit tcp4_proc_exit_net(struct net *net) { remove_proc_entry("tcp", net->proc_net); } static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, }; int __init tcp4_proc_init(void) { return register_pernet_subsys(&tcp4_net_ops); } void tcp4_proc_exit(void) { unregister_pernet_subsys(&tcp4_net_ops); } #endif /* CONFIG_PROC_FS */ /* @wake is one when sk_stream_write_space() calls us. * This sends EPOLLOUT only if notsent_bytes is half the limit. * This mimics the strategy used in sock_def_write_space(). */ bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } EXPORT_SYMBOL(tcp_stream_memory_free); struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v4_pre_connect, .connect = tcp_v4_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v4_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); } static void __net_init tcp_set_hashinfo(struct net *net) { struct inet_hashinfo *hinfo; unsigned int ehash_entries; struct net *old_net; if (net_eq(net, &init_net)) goto fallback; old_net = current->nsproxy->net_ns; ehash_entries = READ_ONCE(old_net->ipv4.sysctl_tcp_child_ehash_entries); if (!ehash_entries) goto fallback; ehash_entries = roundup_pow_of_two(ehash_entries); hinfo = inet_pernet_hashinfo_alloc(&tcp_hashinfo, ehash_entries); if (!hinfo) { pr_warn("Failed to allocate TCP ehash (entries: %u) " "for a netns, fallback to the global one\n", ehash_entries); fallback: hinfo = &tcp_hashinfo; ehash_entries = tcp_hashinfo.ehash_mask + 1; } net->ipv4.tcp_death_row.hashinfo = hinfo; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = ehash_entries / 2; net->ipv4.sysctl_max_syn_backlog = max(128U, ehash_entries / 128); } static int __net_init tcp_sk_init(struct net *net) { net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; net->ipv4.sysctl_tcp_syncookies = 1; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_tw_reuse_delay = 1 * MSEC_PER_SEC; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); tcp_set_hashinfo(net); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; net->ipv4.sysctl_tcp_early_retrans = 3; net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ net->ipv4.sysctl_tcp_retrans_collapse = 1; net->ipv4.sysctl_tcp_max_reordering = 300; net->ipv4.sysctl_tcp_dsack = 1; net->ipv4.sysctl_tcp_app_win = 31; net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ net->ipv4.sysctl_tcp_tso_win_divisor = 3; /* Default TSQ limit of 4 MB */ net->ipv4.sysctl_tcp_limit_output_bytes = 4 << 20; /* rfc5961 challenge ack rate limiting, per net-ns, disabled by default. */ net->ipv4.sysctl_tcp_challenge_ack_limit = INT_MAX; net->ipv4.sysctl_tcp_min_tso_segs = 2; net->ipv4.sysctl_tcp_tso_rtt_log = 9; /* 2^9 = 512 usec */ net->ipv4.sysctl_tcp_min_rtt_wlen = 300; net->ipv4.sysctl_tcp_autocorking = 1; net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; if (net != &init_net) { memcpy(net->ipv4.sysctl_tcp_rmem, init_net.ipv4.sysctl_tcp_rmem, sizeof(init_net.ipv4.sysctl_tcp_rmem)); memcpy(net->ipv4.sysctl_tcp_wmem, init_net.ipv4.sysctl_tcp_wmem, sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_backlog_ack_defer = 1; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Set default values for PLB */ net->ipv4.sysctl_tcp_plb_enabled = 0; /* Disabled by default */ net->ipv4.sysctl_tcp_plb_idle_rehash_rounds = 3; net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; /* Default congestion threshold for PLB to mark a round is 50% */ net->ipv4.sysctl_tcp_plb_cong_thresh = (1 << TCP_PLB_SCALE) / 2; /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; net->ipv4.sysctl_tcp_syn_linear_timeouts = 4; net->ipv4.sysctl_tcp_shrink_window = 0; net->ipv4.sysctl_tcp_pingpong_thresh = 1; net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN); net->ipv4.sysctl_tcp_rto_max_ms = TCP_RTO_MAX_SEC * MSEC_PER_SEC; return 0; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work * and failed setup_net error unwinding path are serialized. * * tcp_twsk_purge() handles twsk in any dead netns, not just those in * net_exit_list, the thread that dismantles a particular twsk must * do so without other thread progressing to refcount_dec_and_test() of * tcp_death_row.tw_refcount. */ mutex_lock(&tcp_exit_batch_mutex); tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) #define INIT_BATCH_SZ 16 static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_tcp_iter_state *iter = priv_data; int err; err = bpf_iter_init_seq_net(priv_data, aux); if (err) return err; err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ); if (err) { bpf_iter_fini_seq_net(priv_data); return err; } return 0; } static void bpf_iter_fini_tcp(void *priv_data) { struct bpf_tcp_iter_state *iter = priv_data; bpf_iter_fini_seq_net(priv_data); kvfree(iter->batch); } static const struct bpf_iter_seq_info tcp_seq_info = { .seq_ops = &bpf_iter_tcp_seq_ops, .init_seq_private = bpf_iter_init_tcp, .fini_seq_private = bpf_iter_fini_tcp, .seq_priv_size = sizeof(struct bpf_tcp_iter_state), }; static const struct bpf_func_proto * bpf_iter_tcp_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sk_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sk_getsockopt_proto; default: return NULL; } } static struct bpf_iter_reg tcp_reg_info = { .target = "tcp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .get_func_proto = bpf_iter_tcp_get_func_proto, .seq_info = &tcp_seq_info, }; static void __init bpf_iter_register(void) { tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]; if (bpf_iter_reg_target(&tcp_reg_info)) pr_warn("Warning: could not register bpf iterator tcp\n"); } #endif void __init tcp_v4_init(void) { int cpu, res; for_each_possible_cpu(cpu) { struct sock *sk; res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_TCP, &init_net); if (res) panic("Failed to create the TCP control socket.\n"); sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); /* Please enforce IP_DF and IPID==0 for RST and * ACK sent in SYN-RECV and TIME-WAIT state. */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; sk->sk_clockid = CLOCK_MONOTONIC; per_cpu(ipv4_tcp_sk.sock, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #endif } |
| 9 9 6 7 7 10 7 10 10 10 10 2132 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 10 10 10 10 10 10 10 10 8 5 6 10 10 10 10 10 9 6 10 10 10 7 7 7 7 7 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/sched/isolation.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the folio has dirty or writeback buffers. If all the buffers * are unlocked and clean then the folio_test_dirty information is stale. If * any of the buffers are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; if (folio_test_writeback(folio)) *writeback = true; bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); put_bh(bh); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct folio *folio; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = ((loff_t)block << blkbits) / PAGE_SIZE; folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio)) goto out; /* * Folio lock protects the buffers. Callers that cannot block * will fallback to serializing vs try_to_free_buffers() via * the i_private_lock. */ if (atomic) spin_lock(&bd_mapping->i_private_lock); else folio_lock(folio); head = folio_buffers(folio); if (!head) goto out_unlock; /* * Upon a noref migration, the folio lock serializes here; * otherwise bail. */ if (test_bit_acquire(BH_Migrate, &head->b_state)) { WARN_ON(!atomic); goto out_unlock; } bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << blkbits); } out_unlock: if (atomic) spin_unlock(&bd_mapping->i_private_lock); else folio_unlock(folio); folio_put(folio); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_read(folio, folio_uptodate); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } struct postprocess_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void verify_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; bool valid; valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, valid); kfree(ctx); } static bool need_fsverity(struct buffer_head *bh) { struct folio *folio = bh->b_folio; struct inode *inode = folio->mapping->host; return fsverity_active(inode) && /* needed by ext4 */ folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); } static void decrypt_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); if (err == 0 && need_fsverity(bh)) { /* * We use different work queues for decryption and for verity * because verity may require reading metadata pages that need * decryption, and we shouldn't recurse to the same workqueue. */ INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); return; } end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { struct inode *inode = bh->b_folio->mapping->host; bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); bool verify = need_fsverity(bh); /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ if (uptodate && (decrypt || verify)) { struct postprocess_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { ctx->bh = bh; if (decrypt) { INIT_WORK(&ctx->work, decrypt_bh); fscrypt_enqueue_decrypt_work(&ctx->work); } else { INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); } return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_folio() - folios which are unlocked * during I/O, and which have the writeback flag cleared upon I/O completion. */ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; BUG_ON(!buffer_async_write(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_writeback(folio); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, * mapping->i_private_list will always be protected by the backing blockdev's * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->i_private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->i_private_list via these * utility functions are free to use i_private_lock and i_private_list for * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.i_private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer * as you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->i_private_data; if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) return 0; return fsync_buffers_list(&buffer_mapping->i_private_lock, &mapping->i_private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /** * generic_buffers_fsync_noflush - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(generic_buffers_fsync_noflush); /** * generic_buffers_fsync - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. This also makes sure that * a device cache flush operation is called at the end. */ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); if (!ret) ret = blkdev_issue_flush(inode->i_sb->s_bdev); return ret; } EXPORT_SYMBOL(generic_buffers_fsync); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh; bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) write_dirty_buffer(bh, 0); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); if (!mapping->i_private_data) { mapping->i_private_data = buffer_mapping; } else { BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /** * block_dirty_folio - Mark a folio as dirty. * @mapping: The address space containing this folio. * @folio: The folio to mark dirty. * * Filesystems which use buffer_heads can use this function as their * ->dirty_folio implementation. Some filesystems need to do a little * work before calling this function. Filesystems which do not use * buffer_heads should call filemap_dirty_folio() instead. * * If the folio has buffers, the uptodate buffers are set dirty, to * preserve dirty-state coherency between the folio and the buffers. * Buffers added to a dirty folio are created dirty. * * The buffers are dirtied before the folio is dirtied. There's a small * race window in which writeback may see the folio cleanness but not the * buffer dirtiness. That's fine. If this code were to set the folio * dirty before the buffers, writeback could clear the folio dirty flag, * see a bunch of clean buffers and we'd end up with dirty buffers/clean * folio on the dirty folio list. * * We use i_private_lock to lock against try_to_free_buffers() while * using the folio's buffer list. This also prevents clean buffers * being added to the folio after it was set dirty. * * Context: May only be called from process context. Does not sleep. * Caller must ensure that @folio cannot be truncated during this call, * typically by holding the folio lock or having a page in the folio * mapped and holding the page table lock. * * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { struct buffer_head *head; bool newly_dirty; spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ newly_dirty = !folio_test_set_dirty(folio); spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(block_dirty_folio); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; LIST_HEAD(tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->i_private_lock); } return ret; } /* * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp) { struct buffer_head *bh, *head; long offset; struct mem_cgroup *memcg, *old_memcg; /* The folio lock pins the memcg */ memcg = folio_memcg(folio); old_memcg = set_active_memcg(memcg); head = NULL; offset = folio_size(folio); while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its folio */ folio_set_bh(bh, folio, offset); } out: set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(folio_alloc_buffers); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct folio *folio, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; folio_attach_private(folio, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev folio's buffers. */ static sector_t folio_init_buffers(struct folio *folio, struct block_device *bdev, unsigned size) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh = head; bool uptodate = folio_test_uptodate(folio); sector_t block = div_u64(folio_pos(folio), size); sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. * * Returns false if we have a failure which cannot be cured by retrying * without sleeping. Returns true if we succeeded, or the caller should retry. */ static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { struct address_space *mapping = bdev->bd_mapping; struct folio *folio; struct buffer_head *bh; sector_t end_block = 0; folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return false; bh = folio_buffers(folio); if (bh) { if (bh->b_size == size) { end_block = folio_init_buffers(folio, bdev, size); goto unlock; } /* * Retrying may succeed; for example the folio may finish * writeback, or buffers may be cleaned. This should not * happen very often; maybe we have old buffers attached to * this blockdev's page cache and we're trying to change * the block size? */ if (!try_to_free_buffers(folio)) { end_block = ~0ULL; goto unlock; } } bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); if (!bh) goto unlock; /* * Link the folio to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ spin_lock(&mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, size); spin_unlock(&mapping->i_private_lock); unlock: folio_unlock(folio); folio_put(folio); return block < end_block; } /* * Create buffers for the specified block device block's folio. If * that folio was dirty, the buffers are set dirty also. Returns false * if we've hit a permanent error. */ static bool grow_buffers(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { loff_t pos; /* * Check for a block which lies outside our maximum possible * pagecache index. */ if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) { printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n", __func__, (unsigned long long)block, bdev); return false; } /* Create a folio with the proper size buffers */ return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { bool blocking = gfpflags_allow_blocking(gfp); /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; if (!grow_buffers(bdev, block, size, gfp)) return NULL; if (blocking) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); if (bh) return bh; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_folio() against that folio will discover all the uptodate * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; if (!folio_test_set_dirty(folio)) { mapping = folio->mapping; if (mapping) __folio_mark_dirty(folio, mapping, 0); } if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); } EXPORT_SYMBOL(mark_buffer_write_io_error); /** * __brelse - Release a buffer. * @bh: The buffer to release. * * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ void __brelse(struct buffer_head *bh) { if (atomic_read(&bh->b_count)) { put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /** * __bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * This variant of bforget() can be called if @bh is guaranteed to not * be NULL. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_folio->mapping; spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); if (cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return NULL; } for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL. Atomic context callers may also return NULL if the buffer is being * migrated; similarly the page is not marked accessed either. */ static struct buffer_head * find_get_block_common(struct block_device *bdev, sector_t block, unsigned size, bool atomic) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block, atomic); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, true); } EXPORT_SYMBOL(__find_get_block); /* same as __find_get_block() but allows sleeping contexts */ struct buffer_head * __find_get_block_nonatomic(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, false); } EXPORT_SYMBOL(__find_get_block_nonatomic); /** * bdev_getblk - Get a buffer_head in a block device's buffer cache. * @bdev: The block device. * @block: The block number. * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * * The returned buffer head has its reference count incremented, but is * not locked. The caller should call brelse() when it has finished * with the buffer. The buffer may not be uptodate. If needed, the * caller can bring it uptodate either by reading it or overwriting it. * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; if (gfpflags_allow_blocking(gfp)) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); might_alloc(gfp); if (bh) return bh; return __getblk_slow(bdev, block, size, gfp); } EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = bdev_getblk(bdev, block, size, GFP_NOWAIT | __GFP_MOVABLE); if (likely(bh)) { bh_readahead(bh, REQ_RAHEAD); brelse(bh); } } EXPORT_SYMBOL(__breadahead); /** * __bread_gfp() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * @gfp: Not page allocation flags; see below. * * You are not expected to call this function. You should use one of * sb_bread(), sb_bread_unmovable() or __bread(). * * Read a specified block, and return the buffer head that refers to it. * If @gfp is 0, the memory will be allocated using the block device's * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be * allocated from a movable area. Do not pass in a complete set of * GFP flags. * * The returned buffer head has its refcount increased. The caller should * call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); /* * Prefer looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp |= __GFP_NOFAIL; bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset) { bh->b_folio = folio; BUG_ON(offset >= folio_size(folio)); if (folio_test_highmem(folio)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = folio_address(folio) + offset; } EXPORT_SYMBOL(folio_set_bh); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = READ_ONCE(bh->b_state); do { } while (!try_cmpxchg_relaxed(&bh->b_state, &b_state, b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } /** * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * * block_invalidate_folio() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; size_t curr_off = 0; size_t stop = length + offset; BUG_ON(!folio_test_locked(folio)); /* * Check for overflow */ BUG_ON(stop > folio_size(folio) || stop < length); head = folio_buffers(folio); if (!head) return; bh = head; do { size_t next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire folio is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == folio_size(folio)) filemap_release_folio(folio, 0); out: folio_clear_mappedtodisk(folio); } EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { if (folio_test_dirty(folio)) set_buffer_dirty(bh); if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } folio_attach_private(folio, head); spin_unlock(&folio->mapping->i_private_lock); return head; } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct folio_batch fbatch; pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; folio_batch_init(&fbatch); while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { count = folio_batch_count(&fbatch); for (i = 0; i < count; i++) { struct folio *folio = fbatch.folios[i]; if (!folio_buffers(folio)) continue; /* * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ folio_lock(folio); /* Recheck when the folio is locked which pins bhs */ head = folio_buffers(folio); if (!head) goto unlock_page; bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); static struct buffer_head *folio_create_buffers(struct folio *folio, struct inode *inode, unsigned int b_state) { struct buffer_head *bh; BUG_ON(!folio_test_locked(folio)); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, 1 << READ_ONCE(inode->i_blkbits), b_state); return bh; } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_folio() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; size_t blocksize; int nr_underway = 0; blk_opf_t write_flags = wbc_to_write_flags(wbc); head = folio_create_buffers(folio, inode, (1 << BH_Dirty) | (1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from block_dirty_folio * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the folio stays dirty. * * Buffers outside i_size may be dirtied by block_dirty_folio; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; block = div_u64(folio_pos(folio), blocksize); last_block = div_u64(i_size_read(inode) - 1, blocksize); /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this folio can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_folio() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the folio. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { folio_redirty_for_writepage(wbc, folio); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The folio and its buffers are protected by the writeback flag, * so we can drop the bh refcounts early. */ BUG_ON(folio_test_writeback(folio)); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); err = 0; done: if (nr_underway == 0) { /* * The folio was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * write_dirty_buffer/submit_bh. A rare case. */ folio_end_writeback(folio); /* * The folio and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The folio is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { /* * The buffer may have been set dirty during * attachment to a dirty folio. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); BUG_ON(folio_test_writeback(folio)); mapping_set_error(folio->mapping, err); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); goto done; } EXPORT_SYMBOL(__block_write_full_folio); /* * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { size_t start, xend; start = max(from, block_start); xend = min(to, block_end); folio_zero_segment(folio, start, xend); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(folio_zero_new_buffers); static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = (loff_t)block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ if (offset >= iomap->offset + iomap->length) return -EIO; switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) { /* * This can happen if truncating the block device races * with the check in the caller as i_size updates on * block devices aren't synchronized by i_rwsem for * block devices. */ if (S_ISBLK(inode->i_mode)) return -EIO; set_buffer_new(bh); } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); return 0; default: WARN_ON_ONCE(1); return -EIO; } } int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { size_t from = offset_in_folio(folio, pos); size_t to = from + len; struct inode *inode = folio->mapping->host; size_t block_start, block_end; sector_t block; int err = 0; size_t blocksize; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!folio_test_locked(folio)); BUG_ON(to > folio_size(folio)); BUG_ON(from > to); head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; block = div_u64(folio_pos(folio), blocksize); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) err = get_block(inode, block, bh, 1); else err = iomap_to_bh(inode, block, bh, iomap); if (err) break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (folio_test_uptodate(folio)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) folio_zero_segments(folio, to, block_end, block_start, from); continue; } } if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) folio_zero_new_buffers(folio, from, to); return err; } int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(folio, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); void block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; unsigned blocksize; struct buffer_head *bh, *head; bh = head = folio_buffers(folio); if (!bh) return; blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the folio went * uptodate as a result of this (potentially partial) write. */ if (!partial) folio_mark_uptodate(folio); } EXPORT_SYMBOL(block_commit_write); /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; int status; folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); status = __block_write_begin_int(folio, pos, len, get_block, NULL); if (unlikely(status)) { folio_unlock(folio); folio_put(folio); folio = NULL; } *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so * we don't have to worry about a read_folio reading them * and overwriting a partial write. However if we have * encountered a short write and only partially written * into a buffer, it will not be marked uptodate, so a * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate folio as a zero-length write, and force the * caller to redo the whole thing. */ if (!folio_test_uptodate(folio)) copied = 0; folio_zero_new_buffers(folio, start+copied, start+len); } flush_dcache_folio(folio); /* This could be a short (even 0-length) commit */ block_commit_write(folio, start, start + copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } folio_unlock(folio); folio_put(folio); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * * Returns true if all buffers which correspond to the specified part * of the folio are uptodate. */ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; bool ret = true; head = folio_buffers(folio); if (!head) return false; blocksize = head->b_size; to = min_t(unsigned, folio_size(folio) - from, count); to = from + to; if (from < blocksize && to > folio_size(folio) - blocksize) return false; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = false; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * folio once IO has completed. */ int block_read_full_folio(struct folio *folio, get_block_t *get_block) { struct inode *inode = folio->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *prev = NULL; size_t blocksize; int fully_mapped = 1; bool page_error = false; loff_t limit = i_size_read(inode); /* This is needed for ext4. */ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) limit = inode->i_sb->s_maxbytes; head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; iblock = div_u64(folio_pos(folio), blocksize); lblock = div_u64(limit + blocksize - 1, blocksize); bh = head; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) page_error = true; } if (!buffer_mapped(bh)) { folio_zero_range(folio, bh_offset(bh), blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } mark_buffer_async_read(bh); if (prev) submit_bh(REQ_OP_READ, prev); prev = bh; } while (iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) folio_set_mappedtodisk(folio); /* * All buffers are uptodate or get_block() returned an error * when trying to map them - we must finish the read because * end_buffer_async_read() will never be called on any buffer * in this folio. */ if (prev) submit_bh(REQ_OP_READ, prev); else folio_end_read(folio, !page_error); return 0; } EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; struct folio *folio; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); struct folio *folio; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = aops->write_begin(file, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = aops->write_begin(file, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(file, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; folio_lock(folio); size = i_size_read(inode); if ((folio->mapping != inode->i_mapping) || (folio_pos(folio) >= size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } end = folio_size(folio); /* folio is wholly or partially inside EOF */ if (folio_pos(folio) + end > size) end = size - folio_pos(folio); ret = __block_write_begin_int(folio, 0, end, get_block, NULL); if (unlikely(ret)) goto out_unlock; block_commit_write(folio, 0, end); folio_mark_dirty(folio); folio_wait_stable(folio); return 0; out_unlock: folio_unlock(folio); return ret; } EXPORT_SYMBOL(block_page_mkwrite); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned blocksize; sector_t iblock; size_t offset, length, pos; struct inode *inode = mapping->host; struct folio *folio; struct buffer_head *bh; int err = 0; blocksize = i_blocksize(inode); length = from & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = bh_read(bh, 0); /* Uhhuh. Read error. Complain and punt. */ if (err < 0) goto unlock; } folio_zero_range(folio, offset, length); mark_buffer_dirty(bh); unlock: folio_unlock(folio); folio_put(folio); return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic write folio function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) { struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); /* Is the folio fully inside i_size? */ if (folio_pos(folio) + folio_size(folio) <= i_size) return __block_write_full_folio(inode, folio, get_block, wbc); /* Is the folio fully outside i_size? (truncate in progress) */ if (folio_pos(folio) >= i_size) { folio_unlock(folio); return 0; /* don't care */ } /* * The folio straddles i_size. It must be zeroed out on each and every * writeback invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); return __block_write_full_folio(inode, folio, get_block, wbc); } sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { const enum req_op op = opf & REQ_OP_MASK; struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); if (buffer_meta(bh)) opf |= REQ_META; if (buffer_prio(bh)) opf |= REQ_PRIO; bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_write_hint = write_hint; bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size); } submit_bio(bio); } void submit_bh(blk_opf_t opf, struct buffer_head *bh) { submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL); } EXPORT_SYMBOL(submit_bh); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | op_flags, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) return -EIO; } else { unlock_buffer(bh); } return 0; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static bool drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; folio_detach_private(folio); return true; failed: return false; } /** * try_to_free_buffers - Release buffers attached to this folio. * @folio: The folio. * * If any buffers are in use (dirty, under writeback, elevated refcount), * no buffers will be freed. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * i_private_lock. * * Exclusion against try_to_free_buffers may be obtained by either * locking the folio or by holding its mapping's i_private_lock. * * Context: Process context. @folio must be locked. Will not sleep. * Return: true if all buffers attached to this folio were freed. */ bool try_to_free_buffers(struct folio *folio) { struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; bool ret = 0; BUG_ON(!folio_test_locked(folio)); if (folio_test_writeback(folio)) return false; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(folio, &buffers_to_free); goto out; } spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty folio. We * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the folio's buffers clean. We discover that here and clean * the folio also. * * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @wait: wait until reading finish * * Returns zero on success or don't wait, and -EIO on error. */ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { int ret = 0; BUG_ON(!buffer_locked(bh)); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ | op_flags, bh); if (wait) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } return ret; } EXPORT_SYMBOL(__bh_read); /** * __bh_read_batch - Submit read for a batch of unlocked buffers * @nr: entry number of the buffer batch * @bhs: a batch of struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @force_lock: force to get a lock on the buffer if set, otherwise drops any * buffer that cannot lock. * * Returns zero on success or don't wait, and -EIO on error. */ void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (buffer_uptodate(bh)) continue; if (force_lock) lock_buffer(bh); else if (!trylock_buffer(bh)) continue; if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } } EXPORT_SYMBOL(__bh_read_batch); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = KMEM_CACHE(buffer_head, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 6 6 6 10 6 6 6 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <linux/crc32c.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_transaction_overhead_buffers: * * Number of blocks each transaction needs for its own bookkeeping */ int j_transaction_overhead_buffers; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size); void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern void jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_folio(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { return jbd2_has_feature_csum2(journal) || jbd2_has_feature_csum3(journal); } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 static inline u32 jbd2_chksum(u32 crc, const void *address, unsigned int length) { return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 29 10 7 6 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Extended to talk the BSD extended IGMP protocol of mrouted 3.6 */ #ifndef _LINUX_IGMP_H #define _LINUX_IGMP_H #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/refcount.h> #include <linux/sockptr.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) { return (struct igmphdr *)skb_transport_header(skb); } static inline struct igmpv3_report * igmpv3_report_hdr(const struct sk_buff *skb) { return (struct igmpv3_report *)skb_transport_header(skb); } static inline struct igmpv3_query * igmpv3_query_hdr(const struct sk_buff *skb) { return (struct igmpv3_query *)skb_transport_header(skb); } struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; __be32 sl_addr[] __counted_by(sl_max); }; #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; this list never used in fast path code */ struct ip_mc_socklist { struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip_sf_list { struct ip_sf_list *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; struct ip_mc_list __rcu *next_rcu; }; struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; char unsolicit_count; char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; unsigned long mca_cstamp; unsigned long mca_tstamp; struct rcu_head rcu; }; /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) return 0; return pskb_may_pull(skb, len); } extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(const struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); } extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 64 64 64 64 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 | // SPDX-License-Identifier: GPL-2.0-only /* * VHT handling * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/export.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "rate.h" static void __check_vhtcap_disable(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap, u32 flag) { __le32 le_flag = cpu_to_le32(flag); if (sdata->u.mgd.vht_capa_mask.vht_cap_info & le_flag && !(sdata->u.mgd.vht_capa.vht_cap_info & le_flag)) vht_cap->cap &= ~flag; } void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap) { int i; u16 rxmcs_mask, rxmcs_cap, rxmcs_n, txmcs_mask, txmcs_cap, txmcs_n; if (!vht_cap->vht_supported) return; if (sdata->vif.type != NL80211_IFTYPE_STATION) return; __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_RXLDPC); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_SHORT_GI_80); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_SHORT_GI_160); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_TXSTBC); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN); __check_vhtcap_disable(sdata, vht_cap, IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN); /* Allow user to decrease AMPDU length exponent */ if (sdata->u.mgd.vht_capa_mask.vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK)) { u32 cap, n; n = le32_to_cpu(sdata->u.mgd.vht_capa.vht_cap_info) & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; n >>= IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT; cap = vht_cap->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; cap >>= IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT; if (n < cap) { vht_cap->cap &= ~IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; vht_cap->cap |= n << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT; } } /* Allow the user to decrease MCSes */ rxmcs_mask = le16_to_cpu(sdata->u.mgd.vht_capa_mask.supp_mcs.rx_mcs_map); rxmcs_n = le16_to_cpu(sdata->u.mgd.vht_capa.supp_mcs.rx_mcs_map); rxmcs_n &= rxmcs_mask; rxmcs_cap = le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); txmcs_mask = le16_to_cpu(sdata->u.mgd.vht_capa_mask.supp_mcs.tx_mcs_map); txmcs_n = le16_to_cpu(sdata->u.mgd.vht_capa.supp_mcs.tx_mcs_map); txmcs_n &= txmcs_mask; txmcs_cap = le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); for (i = 0; i < 8; i++) { u8 m, n, c; m = (rxmcs_mask >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; n = (rxmcs_n >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; c = (rxmcs_cap >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; if (m && ((c != IEEE80211_VHT_MCS_NOT_SUPPORTED && n < c) || n == IEEE80211_VHT_MCS_NOT_SUPPORTED)) { rxmcs_cap &= ~(3 << 2*i); rxmcs_cap |= (rxmcs_n & (3 << 2*i)); } m = (txmcs_mask >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; n = (txmcs_n >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; c = (txmcs_cap >> 2*i) & IEEE80211_VHT_MCS_NOT_SUPPORTED; if (m && ((c != IEEE80211_VHT_MCS_NOT_SUPPORTED && n < c) || n == IEEE80211_VHT_MCS_NOT_SUPPORTED)) { txmcs_cap &= ~(3 << 2*i); txmcs_cap |= (txmcs_n & (3 << 2*i)); } } vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(rxmcs_cap); vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(txmcs_cap); } void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta) { struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; struct ieee80211_sta_vht_cap own_cap; u32 cap_info, i; bool have_80mhz; u32 mpdu_len; memset(vht_cap, 0, sizeof(*vht_cap)); if (!link_sta->pub->ht_cap.ht_supported) return; if (!vht_cap_ie || !sband->vht_cap.vht_supported) return; /* Allow VHT if at least one channel on the sband supports 80 MHz */ have_80mhz = false; for (i = 0; i < sband->n_channels; i++) { if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | IEEE80211_CHAN_NO_80MHZ)) continue; have_80mhz = true; break; } if (!have_80mhz) return; /* * A VHT STA must support 40 MHz, but if we verify that here * then we break a few things - some APs (e.g. Netgear R6300v2 * and others based on the BCM4360 chipset) will unset this * capability bit when operating in 20 MHz. */ vht_cap->vht_supported = true; own_cap = sband->vht_cap; /* * If user has specified capability overrides, take care * of that if the station we're setting up is the AP that * we advertised a restricted capability set to. Override * our own capabilities and then use those below. */ if (sdata->vif.type == NL80211_IFTYPE_STATION && !test_sta_flag(link_sta->sta, WLAN_STA_TDLS_PEER)) ieee80211_apply_vhtcap_overrides(sdata, &own_cap); /* take some capabilities as-is */ cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info); vht_cap->cap = cap_info; vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_VHT_TXOP_PS | IEEE80211_VHT_CAP_HTC_VHT | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB | IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB | IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN | IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN; vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK, own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK); /* and some based on our own capabilities */ switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ: vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; break; default: /* nothing */ break; } /* symmetric capabilities */ vht_cap->cap |= cap_info & own_cap.cap & (IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160); /* remaining ones */ if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE) vht_cap->cap |= cap_info & (IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK); if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE) vht_cap->cap |= cap_info & (IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK); if (own_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE) vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; if (own_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE) vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE; if (own_cap.cap & IEEE80211_VHT_CAP_TXSTBC) vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_RXSTBC_MASK; if (own_cap.cap & IEEE80211_VHT_CAP_RXSTBC_MASK) vht_cap->cap |= cap_info & IEEE80211_VHT_CAP_TXSTBC; /* Copy peer MCS info, the driver might need them. */ memcpy(&vht_cap->vht_mcs, &vht_cap_ie->supp_mcs, sizeof(struct ieee80211_vht_mcs_info)); /* copy EXT_NSS_BW Support value or remove the capability */ if (ieee80211_hw_check(&sdata->local->hw, SUPPORTS_VHT_EXT_NSS_BW)) vht_cap->cap |= (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); else vht_cap->vht_mcs.tx_highest &= ~cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); /* but also restrict MCSes */ for (i = 0; i < 8; i++) { u16 own_rx, own_tx, peer_rx, peer_tx; own_rx = le16_to_cpu(own_cap.vht_mcs.rx_mcs_map); own_rx = (own_rx >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; own_tx = le16_to_cpu(own_cap.vht_mcs.tx_mcs_map); own_tx = (own_tx >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; peer_rx = le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); peer_rx = (peer_rx >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; peer_tx = le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); peer_tx = (peer_tx >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; if (peer_tx != IEEE80211_VHT_MCS_NOT_SUPPORTED) { if (own_rx == IEEE80211_VHT_MCS_NOT_SUPPORTED) peer_tx = IEEE80211_VHT_MCS_NOT_SUPPORTED; else if (own_rx < peer_tx) peer_tx = own_rx; } if (peer_rx != IEEE80211_VHT_MCS_NOT_SUPPORTED) { if (own_tx == IEEE80211_VHT_MCS_NOT_SUPPORTED) peer_rx = IEEE80211_VHT_MCS_NOT_SUPPORTED; else if (own_tx < peer_rx) peer_rx = own_tx; } vht_cap->vht_mcs.rx_mcs_map &= ~cpu_to_le16(IEEE80211_VHT_MCS_NOT_SUPPORTED << i * 2); vht_cap->vht_mcs.rx_mcs_map |= cpu_to_le16(peer_rx << i * 2); vht_cap->vht_mcs.tx_mcs_map &= ~cpu_to_le16(IEEE80211_VHT_MCS_NOT_SUPPORTED << i * 2); vht_cap->vht_mcs.tx_mcs_map |= cpu_to_le16(peer_tx << i * 2); } /* * This is a workaround for VHT-enabled STAs which break the spec * and have the VHT-MCS Rx map filled in with value 3 for all eight * spatial streams, an example is AR9462. * * As per spec, in section 22.1.1 Introduction to the VHT PHY * A VHT STA shall support at least single spatial stream VHT-MCSs * 0 to 7 (transmit and receive) in all supported channel widths. */ if (vht_cap->vht_mcs.rx_mcs_map == cpu_to_le16(0xFFFF)) { vht_cap->vht_supported = false; sdata_info(sdata, "Ignoring VHT IE from %pM (link:%pM) due to invalid rx_mcs_map\n", link_sta->sta->addr, link_sta->addr); return; } /* finally set up the bandwidth */ switch (vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ: link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; break; default: link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_80; if (!(vht_cap->vht_mcs.tx_highest & cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) break; /* * If this is non-zero, then it does support 160 MHz after all, * in one form or the other. We don't distinguish here (or even * above) between 160 and 80+80 yet. */ if (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; } link_sta->pub->bandwidth = ieee80211_sta_cur_vht_bw(link_sta); /* * Work around the Cisco 9115 FW 17.3 bug by taking the min of * both reported MPDU lengths. */ mpdu_len = vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK; if (vht_cap_ie2) mpdu_len = min_t(u32, mpdu_len, le32_get_bits(vht_cap_ie2->vht_cap_info, IEEE80211_VHT_CAP_MAX_MPDU_MASK)); /* * FIXME - should the amsdu len be per link? store per link * and maintain a minimum? */ switch (mpdu_len) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: link_sta->pub->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: link_sta->pub->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_7991; break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: default: link_sta->pub->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_3895; break; } ieee80211_sta_recalc_aggregates(&link_sta->sta->sta); } /* FIXME: move this to some better location - parses HE/EHT now */ static enum ieee80211_sta_rx_bandwidth __ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, struct cfg80211_chan_def *chandef) { unsigned int link_id = link_sta->link_id; struct ieee80211_sub_if_data *sdata = link_sta->sta->sdata; struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; struct ieee80211_sta_he_cap *he_cap = &link_sta->pub->he_cap; struct ieee80211_sta_eht_cap *eht_cap = &link_sta->pub->eht_cap; u32 cap_width; if (he_cap->has_he) { enum nl80211_band band; u8 info; if (chandef) { band = chandef->chan->band; } else { struct ieee80211_bss_conf *link_conf; rcu_read_lock(); link_conf = rcu_dereference(sdata->vif.link_conf[link_id]); band = link_conf->chanreq.oper.chan->band; rcu_read_unlock(); } if (eht_cap->has_eht && band == NL80211_BAND_6GHZ) { info = eht_cap->eht_cap_elem.phy_cap_info[0]; if (info & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) return IEEE80211_STA_RX_BW_320; } info = he_cap->he_cap_elem.phy_cap_info[0]; if (band == NL80211_BAND_2GHZ) { if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) return IEEE80211_STA_RX_BW_40; return IEEE80211_STA_RX_BW_20; } if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G || info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) return IEEE80211_STA_RX_BW_160; if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) return IEEE80211_STA_RX_BW_80; return IEEE80211_STA_RX_BW_20; } if (!vht_cap->vht_supported) return link_sta->pub->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ || cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return IEEE80211_STA_RX_BW_160; /* * If this is non-zero, then it does support 160 MHz after all, * in one form or the other. We don't distinguish here (or even * above) between 160 and 80+80 yet. */ if (vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) return IEEE80211_STA_RX_BW_160; return IEEE80211_STA_RX_BW_80; } enum ieee80211_sta_rx_bandwidth _ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, struct cfg80211_chan_def *chandef) { /* * With RX OMI, also pretend that the STA's capability changed. * Of course this isn't really true, it didn't change, only our * RX capability was changed by notifying RX OMI to the STA. * The purpose, however, is to save power, and that requires * changing also transmissions to the AP and the chanctx. The * transmissions depend on link_sta->bandwidth which is set in * _ieee80211_sta_cur_vht_bw() below, but the chanctx depends * on the result of this function which is also called by * _ieee80211_sta_cur_vht_bw(), so we need to do that here as * well. This is sufficient for the steady state, but during * the transition we already need to change TX/RX separately, * so _ieee80211_sta_cur_vht_bw() below applies the _tx one. */ return min(__ieee80211_sta_cap_rx_bw(link_sta, chandef), link_sta->rx_omi_bw_rx); } enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct link_sta_info *link_sta) { struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; u32 cap_width; if (!vht_cap->vht_supported) { if (!link_sta->pub->ht_cap.ht_supported) return NL80211_CHAN_WIDTH_20_NOHT; return link_sta->pub->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? NL80211_CHAN_WIDTH_40 : NL80211_CHAN_WIDTH_20; } cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ) return NL80211_CHAN_WIDTH_160; else if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return NL80211_CHAN_WIDTH_80P80; return NL80211_CHAN_WIDTH_80; } enum nl80211_chan_width ieee80211_sta_rx_bw_to_chan_width(struct link_sta_info *link_sta) { enum ieee80211_sta_rx_bandwidth cur_bw = link_sta->pub->bandwidth; struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; u32 cap_width; switch (cur_bw) { case IEEE80211_STA_RX_BW_20: if (!link_sta->pub->ht_cap.ht_supported) return NL80211_CHAN_WIDTH_20_NOHT; else return NL80211_CHAN_WIDTH_20; case IEEE80211_STA_RX_BW_40: return NL80211_CHAN_WIDTH_40; case IEEE80211_STA_RX_BW_80: return NL80211_CHAN_WIDTH_80; case IEEE80211_STA_RX_BW_160: cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ) return NL80211_CHAN_WIDTH_160; return NL80211_CHAN_WIDTH_80P80; default: return NL80211_CHAN_WIDTH_20; } } /* FIXME: rename/move - this deals with everything not just VHT */ enum ieee80211_sta_rx_bandwidth _ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta, struct cfg80211_chan_def *chandef) { struct sta_info *sta = link_sta->sta; enum nl80211_chan_width bss_width; enum ieee80211_sta_rx_bandwidth bw; if (chandef) { bss_width = chandef->width; } else { struct ieee80211_bss_conf *link_conf; rcu_read_lock(); link_conf = rcu_dereference(sta->sdata->vif.link_conf[link_sta->link_id]); if (WARN_ON_ONCE(!link_conf)) { rcu_read_unlock(); return IEEE80211_STA_RX_BW_20; } bss_width = link_conf->chanreq.oper.width; rcu_read_unlock(); } /* intentionally do not take rx_bw_omi_rx into account */ bw = __ieee80211_sta_cap_rx_bw(link_sta, chandef); bw = min(bw, link_sta->cur_max_bandwidth); /* but do apply rx_omi_bw_tx */ bw = min(bw, link_sta->rx_omi_bw_tx); /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of * IEEE80211-2016 specification makes higher bandwidth operation * possible on the TDLS link if the peers have wider bandwidth * capability. * * However, in this case, and only if the TDLS peer is authorized, * limit to the tdls_chandef so that the configuration here isn't * wider than what's actually requested on the channel context. */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) && test_sta_flag(sta, WLAN_STA_AUTHORIZED) && sta->tdls_chandef.chan) bw = min(bw, ieee80211_chan_width_to_rx_bw(sta->tdls_chandef.width)); else bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; } void ieee80211_sta_init_nss(struct link_sta_info *link_sta) { u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, eht_rx_nss = 0, rx_nss; bool support_160; if (link_sta->pub->eht_cap.has_eht) { int i; const u8 *rx_nss_mcs = (void *)&link_sta->pub->eht_cap.eht_mcs_nss_supp; /* get the max nss for EHT over all possible bandwidths and mcs */ for (i = 0; i < sizeof(struct ieee80211_eht_mcs_nss_supp); i++) eht_rx_nss = max_t(u8, eht_rx_nss, u8_get_bits(rx_nss_mcs[i], IEEE80211_EHT_MCS_NSS_RX)); } if (link_sta->pub->he_cap.has_he) { int i; u8 rx_mcs_80 = 0, rx_mcs_160 = 0; const struct ieee80211_sta_he_cap *he_cap = &link_sta->pub->he_cap; u16 mcs_160_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); u16 mcs_80_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); for (i = 7; i >= 0; i--) { u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; if (mcs_160 != IEEE80211_HE_MCS_NOT_SUPPORTED) { rx_mcs_160 = i + 1; break; } } for (i = 7; i >= 0; i--) { u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; if (mcs_80 != IEEE80211_HE_MCS_NOT_SUPPORTED) { rx_mcs_80 = i + 1; break; } } support_160 = he_cap->he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; if (support_160) he_rx_nss = min(rx_mcs_80, rx_mcs_160); else he_rx_nss = rx_mcs_80; } if (link_sta->pub->ht_cap.ht_supported) { if (link_sta->pub->ht_cap.mcs.rx_mask[0]) ht_rx_nss++; if (link_sta->pub->ht_cap.mcs.rx_mask[1]) ht_rx_nss++; if (link_sta->pub->ht_cap.mcs.rx_mask[2]) ht_rx_nss++; if (link_sta->pub->ht_cap.mcs.rx_mask[3]) ht_rx_nss++; /* FIXME: consider rx_highest? */ } if (link_sta->pub->vht_cap.vht_supported) { int i; u16 rx_mcs_map; rx_mcs_map = le16_to_cpu(link_sta->pub->vht_cap.vht_mcs.rx_mcs_map); for (i = 7; i >= 0; i--) { u8 mcs = (rx_mcs_map >> (2 * i)) & 3; if (mcs != IEEE80211_VHT_MCS_NOT_SUPPORTED) { vht_rx_nss = i + 1; break; } } /* FIXME: consider rx_highest? */ } rx_nss = max(vht_rx_nss, ht_rx_nss); rx_nss = max(he_rx_nss, rx_nss); rx_nss = max(eht_rx_nss, rx_nss); rx_nss = max_t(u8, 1, rx_nss); link_sta->capa_nss = rx_nss; /* that shouldn't be set yet, but we can handle it anyway */ if (link_sta->op_mode_nss) link_sta->pub->rx_nss = min_t(u8, rx_nss, link_sta->op_mode_nss); else link_sta->pub->rx_nss = rx_nss; } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct link_sta_info *link_sta, u8 opmode, enum nl80211_band band) { enum ieee80211_sta_rx_bandwidth new_bw; struct sta_opmode_info sta_opmode = {}; u32 changed = 0; u8 nss; /* ignore - no support for BF yet */ if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF) return 0; nss = opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_MASK; nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT; nss += 1; if (link_sta->op_mode_nss != nss) { if (nss <= link_sta->capa_nss) { link_sta->op_mode_nss = nss; if (nss != link_sta->pub->rx_nss) { link_sta->pub->rx_nss = nss; changed |= IEEE80211_RC_NSS_CHANGED; sta_opmode.rx_nss = link_sta->pub->rx_nss; sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; } } else { pr_warn_ratelimited("Ignoring NSS change in VHT Operating Mode Notification from %pM with invalid nss %d", link_sta->pub->addr, nss); } } switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: /* ignore IEEE80211_OPMODE_NOTIF_BW_160_80P80 must not be set */ link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_20; break; case IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: /* ignore IEEE80211_OPMODE_NOTIF_BW_160_80P80 must not be set */ link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_40; break; case IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: if (opmode & IEEE80211_OPMODE_NOTIF_BW_160_80P80) link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; else link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_80; break; case IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: /* legacy only, no longer used by newer spec */ link_sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; break; } new_bw = ieee80211_sta_cur_vht_bw(link_sta); if (new_bw != link_sta->pub->bandwidth) { link_sta->pub->bandwidth = new_bw; sta_opmode.bw = ieee80211_sta_rx_bw_to_chan_width(link_sta); changed |= IEEE80211_RC_BW_CHANGED; sta_opmode.changed |= STA_OPMODE_MAX_BW_CHANGED; } if (sta_opmode.changed) cfg80211_sta_opmode_change_notify(sdata->dev, link_sta->addr, &sta_opmode, GFP_KERNEL); return changed; } void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct ieee80211_mgmt *mgmt) { struct ieee80211_bss_conf *link_conf = link->conf; if (!link_conf->mu_mimo_owner) return; if (!memcmp(mgmt->u.action.u.vht_group_notif.position, link_conf->mu_group.position, WLAN_USER_POSITION_LEN) && !memcmp(mgmt->u.action.u.vht_group_notif.membership, link_conf->mu_group.membership, WLAN_MEMBERSHIP_LEN)) return; memcpy(link_conf->mu_group.membership, mgmt->u.action.u.vht_group_notif.membership, WLAN_MEMBERSHIP_LEN); memcpy(link_conf->mu_group.position, mgmt->u.action.u.vht_group_notif.position, WLAN_USER_POSITION_LEN); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_MU_GROUPS); } void ieee80211_update_mu_groups(struct ieee80211_vif *vif, unsigned int link_id, const u8 *membership, const u8 *position) { struct ieee80211_bss_conf *link_conf; rcu_read_lock(); link_conf = rcu_dereference(vif->link_conf[link_id]); if (!WARN_ON_ONCE(!link_conf || !link_conf->mu_mimo_owner)) { memcpy(link_conf->mu_group.membership, membership, WLAN_MEMBERSHIP_LEN); memcpy(link_conf->mu_group.position, position, WLAN_USER_POSITION_LEN); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_update_mu_groups); void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct link_sta_info *link_sta, u8 opmode, enum nl80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; u32 changed = __ieee80211_vht_handle_opmode(sdata, link_sta, opmode, band); if (changed > 0) { ieee80211_recalc_min_chandef(sdata, link_sta->link_id); rate_control_rate_update(local, sband, link_sta, changed); } } void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, u16 vht_mask[NL80211_VHT_NSS_MAX]) { int i; u16 mask, cap = le16_to_cpu(vht_cap); for (i = 0; i < NL80211_VHT_NSS_MAX; i++) { mask = (cap >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; switch (mask) { case IEEE80211_VHT_MCS_SUPPORT_0_7: vht_mask[i] = 0x00FF; break; case IEEE80211_VHT_MCS_SUPPORT_0_8: vht_mask[i] = 0x01FF; break; case IEEE80211_VHT_MCS_SUPPORT_0_9: vht_mask[i] = 0x03FF; break; case IEEE80211_VHT_MCS_NOT_SUPPORTED: default: vht_mask[i] = 0; break; } } } |
| 17 17 17 17 28 28 28 28 28 15 15 15 15 37 28 28 28 37 28 15 15 15 15 3 4 4 4 4 4 4 4 4 3 4 4 37 37 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "send.h" #include "main.h" #include <linux/atomic.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "log.h" #include "mesh-interface.h" #include "network-coding.h" #include "originator.h" #include "routing.h" #include "translation-table.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /** * batadv_send_skb_packet() - send an already prepared packet * @skb: the packet to send * @hard_iface: the interface to use to send the broadcast packet * @dst_addr: the payload destination * * Send out an already prepared packet to the given neighbor or broadcast it * using the specified interface. Either hard_iface or neigh_node must be not * NULL. * If neigh_node is NULL, then the packet is broadcasted using hard_iface, * otherwise it is sent as unicast to the given neighbor. * * Regardless of the return value, the skb is consumed. * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const u8 *dst_addr) { struct batadv_priv *bat_priv; struct ethhdr *ethhdr; int ret; bat_priv = netdev_priv(hard_iface->mesh_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { pr_warn("Interface %s is not up - can't send packet via that interface!\n", hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->protocol = htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* Save a clone of the skb to use when decoding coded packets */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP * (which is > 0). This will not be treated as an error. */ ret = dev_queue_xmit(skb); return net_xmit_eval(ret); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } /** * batadv_send_broadcast_skb() - Send broadcast packet via hard interface * @skb: packet to be transmitted (with batadv header and no outer eth header) * @hard_iface: outgoing interface * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { static const u8 broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; return batadv_send_skb_packet(skb, hard_iface, broadcast_addr); } /** * batadv_send_unicast_skb() - Send unicast packet to neighbor * @skb: packet to be transmitted (with batadv header and no outer eth header) * @neigh: neighbor which is used as next hop to destination * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh) { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hardif_neigh_node *hardif_neigh; #endif int ret; ret = batadv_send_skb_packet(skb, neigh->if_incoming, neigh->addr); #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; batadv_hardif_neigh_put(hardif_neigh); #endif return ret; } /** * batadv_send_skb_to_orig() - Lookup next-hop and transmit skb. * @skb: Packet to be transmitted. * @orig_node: Final destination of the packet. * @recv_if: Interface used when receiving the packet (can be NULL). * * Looks up the best next-hop towards the passed originator and passes the * skb on for preparation of MAC header. If the packet originated from this * host, NULL can be passed as recv_if and no interface alternating is * attempted. * * Return: negative errno code on a failure, -EINPROGRESS if the skb is * buffered for later transmit or the NET_XMIT status returned by the * lower routine if the packet has been passed down. */ int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; int ret; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) { ret = -EINVAL; goto free_skb; } /* Check if the skb is too large to send in one piece and fragment * it if needed. */ if (atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { /* Fragment and send packet. */ ret = batadv_frag_send_packet(skb, orig_node, neigh_node); /* skb was consumed */ skb = NULL; goto put_neigh_node; } /* try to network code the packet, if it is received on an interface * (i.e. being forwarded). If the packet originates from this node or if * network coding fails, then send the packet as usual. */ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) ret = -EINPROGRESS; else ret = batadv_send_unicast_skb(skb, neigh_node); /* skb was consumed */ skb = NULL; put_neigh_node: batadv_neigh_node_put(neigh_node); free_skb: kfree_skb(skb); return ret; } /** * batadv_send_skb_push_fill_unicast() - extend the buffer and initialize the * common fields for unicast packets * @skb: the skb carrying the unicast header to initialize * @hdr_size: amount of bytes to push at the beginning of the skb * @orig_node: the destination node * * Return: false if the buffer extension was not possible or true otherwise. */ static bool batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ unicast_packet->packet_type = BATADV_UNICAST; /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; return true; } /** * batadv_send_skb_prepare_unicast() - encapsulate an skb with a unicast header * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * * Return: false if the payload could not be encapsulated or true otherwise. */ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb, struct batadv_orig_node *orig_node) { size_t uni_size = sizeof(struct batadv_unicast_packet); return batadv_send_skb_push_fill_unicast(skb, uni_size, orig_node); } /** * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a * unicast 4addr header * @bat_priv: the bat priv with all the mesh interface information * @skb: the skb containing the payload to encapsulate * @orig: the destination node * @packet_subtype: the unicast 4addr packet subtype to use * * Return: false if the payload could not be encapsulated or true otherwise. */ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig, int packet_subtype) { struct batadv_hard_iface *primary_if; struct batadv_unicast_4addr_packet *uc_4addr_packet; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* Pull the header space and fill the unicast_packet substructure. * We can do that because the first member of the uc_4addr_packet * is of type struct unicast_packet */ if (!batadv_send_skb_push_fill_unicast(skb, sizeof(*uc_4addr_packet), orig)) goto out; uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; ret = true; out: batadv_hardif_put(primary_if); return ret; } /** * batadv_send_skb_unicast() - encapsulate and send an skb via unicast * @bat_priv: the bat priv with all the mesh interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @orig_node: the originator to send the packet to * @vid: the vid to be used to search the translation table * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) goto out; switch (packet_type) { case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It * should never be invoked with any other packet type */ goto out; } /* skb->data might have been reallocated by * batadv_send_skb_prepare_unicast{,_4addr}() */ ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less * than the current one */ if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) unicast_packet->ttvn = unicast_packet->ttvn - 1; ret = batadv_send_skb_to_orig(skb, orig_node, NULL); /* skb was consumed */ skb = NULL; out: kfree_skb(skb); return ret; } /** * batadv_send_skb_via_tt_generic() - send an skb via TT lookup * @bat_priv: the bat priv with all the mesh interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet * header via the translation table. Wrap the given skb into a batman-adv * unicast or unicast-4addr header depending on whether BATADV_UNICAST or * BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame * to the according destination node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; /* if we got an hint! let's send the packet to this client (if any) */ if (dst_hint) { src = NULL; dst = dst_hint; } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_send_skb_via_gw() - send an skb via gateway lookup * @bat_priv: the bat priv with all the mesh interface information * @skb: payload to send * @vid: the vid to be used to search the translation table * * Look up the currently selected gateway. Wrap the given skb into a batman-adv * unicast header and send this frame to this gateway node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, bool dropped) { if (dropped) kfree_skb(forw_packet->skb); else consume_skb(forw_packet->skb); batadv_hardif_put(forw_packet->if_incoming); batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); } /** * batadv_forw_packet_alloc() - allocate a forwarding packet * @if_incoming: The (optional) if_incoming to be grabbed * @if_outgoing: The (optional) if_outgoing to be grabbed * @queue_left: The (optional) queue counter to decrease * @bat_priv: The bat_priv for the mesh of this forw_packet * @skb: The raw packet this forwarding packet shall contain * * Allocates a forwarding packet and tries to get a reference to the * (optional) if_incoming, if_outgoing and queue_left. If queue_left * is NULL then bat_priv is optional, too. * * Return: An allocated forwarding packet on success, NULL otherwise. */ struct batadv_forw_packet * batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, atomic_t *queue_left, struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_forw_packet *forw_packet; const char *qname; if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { qname = "unknown"; if (queue_left == &bat_priv->bcast_queue_left) qname = "bcast"; if (queue_left == &bat_priv->batman_queue_left) qname = "batman"; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s queue is full\n", qname); return NULL; } forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto err; if (if_incoming) kref_get(&if_incoming->refcount); if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&forw_packet->list); INIT_HLIST_NODE(&forw_packet->cleanup_list); forw_packet->skb = skb; forw_packet->queue_left = queue_left; forw_packet->if_incoming = if_incoming; forw_packet->if_outgoing = if_outgoing; forw_packet->num_packets = 1; return forw_packet; err: if (queue_left) atomic_inc(queue_left); return NULL; } /** * batadv_forw_packet_was_stolen() - check whether someone stole this packet * @forw_packet: the forwarding packet to check * * This function checks whether the given forwarding packet was claimed by * someone else for free(). * * Return: True if someone stole it, false otherwise. */ static bool batadv_forw_packet_was_stolen(struct batadv_forw_packet *forw_packet) { return !hlist_unhashed(&forw_packet->cleanup_list); } /** * batadv_forw_packet_steal() - claim a forw_packet for free() * @forw_packet: the forwarding packet to steal * @lock: a key to the store to steal from (e.g. forw_{bat,bcast}_list_lock) * * This function tries to steal a specific forw_packet from global * visibility for the purpose of getting it for free(). That means * the caller is *not* allowed to requeue it afterwards. * * Return: True if stealing was successful. False if someone else stole it * before us. */ bool batadv_forw_packet_steal(struct batadv_forw_packet *forw_packet, spinlock_t *lock) { /* did purging routine steal it earlier? */ spin_lock_bh(lock); if (batadv_forw_packet_was_stolen(forw_packet)) { spin_unlock_bh(lock); return false; } hlist_del_init(&forw_packet->list); /* Just to spot misuse of this function */ hlist_add_fake(&forw_packet->cleanup_list); spin_unlock_bh(lock); return true; } /** * batadv_forw_packet_list_steal() - claim a list of forward packets for free() * @forw_list: the to be stolen forward packets * @cleanup_list: a backup pointer, to be able to dispose the packet later * @hard_iface: the interface to steal forward packets from * * This function claims responsibility to free any forw_packet queued on the * given hard_iface. If hard_iface is NULL forwarding packets on all hard * interfaces will be claimed. * * The packets are being moved from the forw_list to the cleanup_list. This * makes it possible for already running threads to notice the claim. */ static void batadv_forw_packet_list_steal(struct hlist_head *forw_list, struct hlist_head *cleanup_list, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, forw_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if (hard_iface && forw_packet->if_incoming != hard_iface && forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); hlist_add_head(&forw_packet->cleanup_list, cleanup_list); } } /** * batadv_forw_packet_list_free() - free a list of forward packets * @head: a list of to be freed forw_packets * * This function cancels the scheduling of any packet in the provided list, * waits for any possibly running packet forwarding thread to finish and * finally, safely frees this forward packet. * * This function might sleep. */ static void batadv_forw_packet_list_free(struct hlist_head *head) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, head, cleanup_list) { cancel_delayed_work_sync(&forw_packet->delayed_work); hlist_del(&forw_packet->cleanup_list); batadv_forw_packet_free(forw_packet, true); } } /** * batadv_forw_packet_queue() - try to queue a forwarding packet * @forw_packet: the forwarding packet to queue * @lock: a key to the store (e.g. forw_{bat,bcast}_list_lock) * @head: the shelve to queue it on (e.g. forw_{bat,bcast}_list) * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a forwarding packet. Requeuing * is prevented if the according interface is shutting down * (e.g. if batadv_forw_packet_list_steal() was called for this * packet earlier). * * Calling batadv_forw_packet_queue() after a call to * batadv_forw_packet_steal() is forbidden! * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet, spinlock_t *lock, struct hlist_head *head, unsigned long send_time) { spin_lock_bh(lock); /* did purging routine steal it from us? */ if (batadv_forw_packet_was_stolen(forw_packet)) { /* If you got it for free() without trouble, then * don't get back into the queue after stealing... */ WARN_ONCE(hlist_fake(&forw_packet->cleanup_list), "Requeuing after batadv_forw_packet_steal() not allowed!\n"); spin_unlock_bh(lock); return; } hlist_del_init(&forw_packet->list); hlist_add_head(&forw_packet->list, head); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time - jiffies); spin_unlock_bh(lock); } /** * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet * @bat_priv: the bat priv with all the mesh interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a broadcast packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bcast_list_lock, &bat_priv->forw_bcast_list, send_time); } /** * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet * @bat_priv: the bat priv with all the mesh interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue an OGMv1 packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bat_list_lock, &bat_priv->forw_bat_list, send_time); } /** * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to queue on * * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { struct batadv_forw_packet *forw_packet; unsigned long send_time = jiffies; struct sk_buff *newskb; newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); if (!forw_packet) goto err_packet_free; forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); send_time += delay ? delay : msecs_to_jiffies(5); batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: kfree_skb(newskb); err: return NETDEV_TX_BUSY; } /** * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to forward to * * Transmits a broadcast packet on the specified interface either immediately * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { unsigned int num_bcasts = if_out->num_bcasts; struct sk_buff *newskb; int ret = NETDEV_TX_OK; if (!delay) { newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; batadv_send_broadcast_skb(newskb, if_out); num_bcasts--; } /* delayed broadcast or rebroadcasts? */ if (num_bcasts >= 1) { BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, own_packet, if_in, if_out); } return ret; } /** * batadv_send_no_broadcast() - check whether (re)broadcast is necessary * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to check * @own_packet: true if it is a self-generated broadcast packet * @if_out: the outgoing interface checked and considered for (re)broadcast * * Return: False if a packet needs to be (re)broadcasted on the given interface, * true otherwise. */ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, struct sk_buff *skb, bool own_packet, struct batadv_hard_iface *if_out) { struct batadv_hardif_neigh_node *neigh_node = NULL; struct batadv_bcast_packet *bcast_packet; u8 *orig_neigh; u8 *neigh_addr; char *type; int ret; if (!own_packet) { neigh_addr = eth_hdr(skb)->h_source; neigh_node = batadv_hardif_neigh_get(if_out, neigh_addr); } bcast_packet = (struct batadv_bcast_packet *)skb->data; orig_neigh = neigh_node ? neigh_node->orig : NULL; ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) return false; /* no broadcast */ switch (ret) { case BATADV_HARDIF_BCAST_NORECIPIENT: type = "no neighbor"; break; case BATADV_HARDIF_BCAST_DUPFWD: type = "single neighbor is source"; break; case BATADV_HARDIF_BCAST_DUPORIG: type = "single neighbor is originator"; break; default: type = "unknown"; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, if_out->net_dev->name, type); return true; } /** * __batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the given skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if; int ret = NETDEV_TX_OK; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return NETDEV_TX_BUSY; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->mesh_iface != bat_priv->mesh_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; if (batadv_send_no_broadcast(bat_priv, skb, own_packet, hard_iface)) { batadv_hardif_put(hard_iface); continue; } ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, own_packet, primary_if, hard_iface); batadv_hardif_put(hard_iface); if (ret == NETDEV_TX_BUSY) break; } rcu_read_unlock(); batadv_hardif_put(primary_if); return ret; } /** * batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); } /** * batadv_send_bcast_packet() - send and queue a broadcast packet * @bat_priv: the bat priv with all the mesh interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Consumes the provided skb. */ void batadv_send_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); consume_skb(skb); } /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check * * Checks whether a given packet has any (re)transmissions left on the provided * interface. * * hard_iface may be NULL: In that case the number of transmissions this skb had * so far is compared with the maximum amount of retransmissions independent of * any interface instead. * * Return: True if (re)transmissions are left, false otherwise. */ static bool batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet * @forw_packet: the packet to decrease the counter for */ static void batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** * batadv_forw_packet_is_rebroadcast() - check packet for previous transmissions * @forw_packet: the packet to check * * Return: True if this packet was transmitted before, false otherwise. */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; return num_bcasts != forw_packet->if_outgoing->num_bcasts; } /** * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet * @work: work queue item * * Transmits a queued broadcast packet and if necessary reschedules it. */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct sk_buff *skb1; bool dropped = false; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->mesh_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; goto out; } if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) { dropped = true; goto out; } /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (!skb1) goto out; batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); batadv_forw_packet_bcasts_dec(forw_packet); if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; } out: /* do we get something for free()? */ if (batadv_forw_packet_steal(forw_packet, &bat_priv->forw_bcast_list_lock)) batadv_forw_packet_free(forw_packet, dropped); } /** * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on * * This method cancels and purges any broadcast and OGMv1 packet on the given * hard_iface. If hard_iface is NULL, broadcast and OGMv1 packets on all hard * interfaces will be canceled and purged. * * This function might sleep. */ void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct hlist_head head = HLIST_HEAD_INIT; if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s(): %s\n", __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bcast_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* claim batman packet list for free() */ spin_lock_bh(&bat_priv->forw_bat_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bat_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bat_list_lock); /* then cancel or wait for packet workers to finish and free */ batadv_forw_packet_list_free(&head); } |
| 56 55 56 43 56 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); err_unlock: rcu_read_unlock(); return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & F |